[1] S. Mehraeen, S. Jagannathan, and M. L. Crow, "Novel Dynamic Representation and Control of Power Systems With FACTS Devices," Ieee Transactions on Power Systems, vol. 25, no. 3, pp. 1542-1554, Aug.2010.
Abstract: FACTS devices have been shown to be useful in damping power system oscillations. However, in large power systems, the FACTS control design is complex due to the combination of differential and algebraic equations required to model the power system. In this paper, a new method to generate a nonlinear dynamic representation of the power network is introduced to enable more sophisticated control design. Once the new representation is obtained, a back stepping methodology for the UPFC is utilized to mitigate the generator oscillations. Finally, the neural network approximation property is utilized to relax the need for knowledge of the power system topology and to approximate the nonlinear uncertainties. The net result is a power system representation that can be used for the design of an enhanced FACTS control scheme. Simulation results are given to validate the theoretical conjectures
Abstract: FACTS devices have been shown to be useful in damping power system oscillations. However, in large power systems, the FACTS control design is complex due to the combination of differential and algebraic equations required to model the power system. In this paper, a new method to generate a nonlinear dynamic representation of the power network is introduced to enable more sophisticated control design. Once the new representation is obtained, a back stepping methodology for the UPFC is utilized to mitigate the generator oscillations. Finally, the neural network approximation property is utilized to relax the need for knowledge of the power system topology and to approximate the nonlinear uncertainties. The net result is a power system representation that can be used for the design of an enhanced FACTS control scheme. Simulation results are given to validate the theoretical conjectures
[2] S. C. Marchiori, M. D. G. da Silveira, A. D. P. Lotufo, C. R. Minussi, and M. L. M. Lopes, "Neural network based on adaptive resonance theory with continuous training for multi-configuration transient stability analysis of electric power systems," Applied Soft Computing, vol. 11, no. 1, pp. 706-715, Jan.2011.
Abstract: This work presents a methodology to analyze electric power systems transient stability for first swing using a neural network based on adaptive resonance theory (ART) architecture, called Euclidean ARTMAP neural network. The ART architectures present plasticity and stability characteristics, which are very important for the training and to execute the analysis in a fast way. The Euclidean ARTMAP version provides more accurate and faster solutions, when compared to the fuzzy ARTMAP configuration. Three steps are necessary for the network working, training, analysis and continuous training. The training step requires much effort (processing) while the analysis is effectuated almost without computational effort. The proposed network allows approaching several topologies of the electric system at the same time; therefore it is an alternative for real time transient stability of electric power systems. To illustrate the proposed neural network an application is presented for a multi-machine electric power systems composed of 10 synchronous machines, 45 buses and 73 transmission lines.
Abstract: This work presents a methodology to analyze electric power systems transient stability for first swing using a neural network based on adaptive resonance theory (ART) architecture, called Euclidean ARTMAP neural network. The ART architectures present plasticity and stability characteristics, which are very important for the training and to execute the analysis in a fast way. The Euclidean ARTMAP version provides more accurate and faster solutions, when compared to the fuzzy ARTMAP configuration. Three steps are necessary for the network working, training, analysis and continuous training. The training step requires much effort (processing) while the analysis is effectuated almost without computational effort. The proposed network allows approaching several topologies of the electric system at the same time; therefore it is an alternative for real time transient stability of electric power systems. To illustrate the proposed neural network an application is presented for a multi-machine electric power systems composed of 10 synchronous machines, 45 buses and 73 transmission lines.
[3] S. Jazebi, H. R. Baghaee, and G. B. Gharehpetian, "Optimal Variable-Gain Neural Network-Based UPFC Controller by Means of Differential Evolution Algorithm," International Review of Electrical Engineering-Iree, vol. 5, no. 3, pp. 1069-1077, May2010.
Abstract: This paper presents a modified control strategy for a Unified Power flow Controller (UPFC). UPFC is one of the most promising FACTS devices to control power system oscillations and enhancing the transient stability. Power systems, always contains parametric uncertainties which must be considered in controller designs. Variations of power system operating conditions could move parameter region of UPFC controllers in its parameter space. Focus of present study is to investigate two main functions: (1) prevent interactions caused by inappropriate setting of UPFC controller's parameters by using differential evolution algorithm; (2) how to conclude the optimized controller's parameters in the model preventing delays caused by DEA slow convergence response. In this paper, a novel gain-varied control for UPFC based on artificial neural network (ANN) and k-means clustering algorithm is proposed and compared with a conventional PI controller. Simulation results developed in MATLAB-SIMULINK environment verify the viability and effectiveness of proposed control scheme in comparison with conventional PI controller.
[4] N. Amjady and S. A. Banihashemi, "Transient stability prediction of power systems by a new synchronism status index and hybrid classifier," Iet Generation Transmission & Distribution, vol. 4, no. 4, pp. 509-518, Apr.2010.
Abstract: In this study, a new transient stability prediction method is proposed. The measured rotor angles of generators are first processed by a new non-linear transformation based on hyperbolic functions to construct a novel synchronism status index. The transformed rotor angles are then applied as input data to a hybrid classifier composed of an array of parallel probabilistic neural networks in which one probabilistic neural network is assigned to each unit of the power system. The proposed hybrid classifier can predict transient stability status of power system and determine tripped machines. The efficiency of the proposed solution method for transient stability prediction is studied based on the IEEE 162-bus and IEEE 145-bus test systems. Moreover, the effectiveness of the method under varied configurations of the power system is also shown
Abstract: In this study, a new transient stability prediction method is proposed. The measured rotor angles of generators are first processed by a new non-linear transformation based on hyperbolic functions to construct a novel synchronism status index. The transformed rotor angles are then applied as input data to a hybrid classifier composed of an array of parallel probabilistic neural networks in which one probabilistic neural network is assigned to each unit of the power system. The proposed hybrid classifier can predict transient stability status of power system and determine tripped machines. The efficiency of the proposed solution method for transient stability prediction is studied based on the IEEE 162-bus and IEEE 145-bus test systems. Moreover, the effectiveness of the method under varied configurations of the power system is also shown
[5] P. Li, J. Lam, and Z. Shu, "On the Transient and Steady-State Estimates of Interval Genetic Regulatory Networks," Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics, vol. 40, no. 2, pp. 336-349, Apr.2010.
Abstract: This paper is concerned with the transient and steady-state estimates of a class of genetic regulatory networks (GRNs). Some sufficient conditions, which do not only present the transient estimate but also provide the estimates of decay rate and decay coefficient of the GRN with interval parameter uncertainties ( interval GRN), are established by means of linear matrix inequality (LMI) and Lyapunov-Krasovskii functional. Moreover, the steady-state estimate of the proposed GRN model is also investigated. Furthermore, it is well known that gene regulation is an intrinsically noisy process due to intracellular and extracellular noise perturbations and environmental fluctuations. Then, by utilizing stochastic differential equation theory, the obtained results are extended to the case with noise perturbations due to natural random fluctuations. All the conditions are expressed within the framework of LMIs, which can easily be computed by using standard numerical software. A three-gene network is provided to illustrate the effectiveness of the theoretical results
Abstract: This paper is concerned with the transient and steady-state estimates of a class of genetic regulatory networks (GRNs). Some sufficient conditions, which do not only present the transient estimate but also provide the estimates of decay rate and decay coefficient of the GRN with interval parameter uncertainties ( interval GRN), are established by means of linear matrix inequality (LMI) and Lyapunov-Krasovskii functional. Moreover, the steady-state estimate of the proposed GRN model is also investigated. Furthermore, it is well known that gene regulation is an intrinsically noisy process due to intracellular and extracellular noise perturbations and environmental fluctuations. Then, by utilizing stochastic differential equation theory, the obtained results are extended to the case with noise perturbations due to natural random fluctuations. All the conditions are expressed within the framework of LMIs, which can easily be computed by using standard numerical software. A three-gene network is provided to illustrate the effectiveness of the theoretical results
[6] R. A. Hooshmand and G. Isazadeh, "Application of adaptive Lyapunov-based UPFC supplementary controller by neural network algorithm in multi-machine power system," Electrical Engineering, vol. 91, no. 4-5, pp. 187-195, Dec.2009.
Abstract: In this paper, a new adaptive unified power flow controller (UPFC) based on the Lyapunov method and neural network structure is presented. The corresponding energy function is derived for the single machine infinitive bus system with classic generator model representation. Damping control strategy to improve transient behavior of the system is determined by considering the dynamic modeling of the UPFC. The Lyapunov-based controller is extended to interconnected power system by considering the two-machine equivalent model and the center of inertia concept. The recurrent neural network (RNN) with back propagation algorithm is also used to overcome the uncertainty issues and also to consider the more detailed power system. The designed Lyapunov-RNN-based controller is applied to the interconnected power system between the Esfahan-Yazd region transmission network in Iran power system. The performance of the proposed controller is compared with other different controllers by applying some disturbances in the system. Finally, simulation results are presented and the effectiveness of the proposed method for power system stability enhancement is discussed as well
Abstract: In this paper, a new adaptive unified power flow controller (UPFC) based on the Lyapunov method and neural network structure is presented. The corresponding energy function is derived for the single machine infinitive bus system with classic generator model representation. Damping control strategy to improve transient behavior of the system is determined by considering the dynamic modeling of the UPFC. The Lyapunov-based controller is extended to interconnected power system by considering the two-machine equivalent model and the center of inertia concept. The recurrent neural network (RNN) with back propagation algorithm is also used to overcome the uncertainty issues and also to consider the more detailed power system. The designed Lyapunov-RNN-based controller is applied to the interconnected power system between the Esfahan-Yazd region transmission network in Iran power system. The performance of the proposed controller is compared with other different controllers by applying some disturbances in the system. Finally, simulation results are presented and the effectiveness of the proposed method for power system stability enhancement is discussed as well
[7] T. T. Ma, "Multiple Upfc Damping Control Scheme Using Ann Coordinated Adaptive Controllers," Asian Journal of Control, vol. 11, no. 5, pp. 489-502, Sept.2009.
Abstract: This paper presents a novel design of all adaptive damping control scheme using artificial neural network (ANN) coordinated Multiple unified power flow controllers (UPFCs). In this study, a centralized global control scheme is proposed in which three UPFCs are first assumed to be strategically installed in the system to achieve it steady state power flow control objective, then utilized to demonstrate the proposed control scheme ill enhancing the damping of low frequency electromechanical oscillations exhibited by a three-area, six-machine power system. The coordination of controllers is accomplished by a genetic algorithm based tuning process that is based oil considering various system operating conditions and minimizing a set of pre-defined coordinated damping performance indices (CDPI). The task of real-time adaptation of system uncertainties is carried out using a trained ANN as an adaptive coordinator to achieve the robust control objectives
Abstract: This paper presents a novel design of all adaptive damping control scheme using artificial neural network (ANN) coordinated Multiple unified power flow controllers (UPFCs). In this study, a centralized global control scheme is proposed in which three UPFCs are first assumed to be strategically installed in the system to achieve it steady state power flow control objective, then utilized to demonstrate the proposed control scheme ill enhancing the damping of low frequency electromechanical oscillations exhibited by a three-area, six-machine power system. The coordination of controllers is accomplished by a genetic algorithm based tuning process that is based oil considering various system operating conditions and minimizing a set of pre-defined coordinated damping performance indices (CDPI). The task of real-time adaptation of system uncertainties is carried out using a trained ANN as an adaptive coordinator to achieve the robust control objectives
[8] T. Allaoui, C. Belfedal, M. A. Denai, and M. Bouhamida, "Adaptive State Feedback and Decoupling MIMO GPC Control of 3-Levels UPFC for Improvement of Transient Stability Performance," International Review of Electrical Engineering-Iree, vol. 3, no. 3, pp. 435-443, May2008.
Abstract: This paper investigates control methods for the 3 level unified power flow controller in order to improve the stability of a power system hence providing security under increased power flow conditions. These include a direct PI controller with decoupling (PI), Adaptive state feedback based on multivariable Elman neural network (MIMO-NSF) and multivariable GPC with decoupling algorithm (MIMO-GPC). The performances of these controllers are evaluated under different operating conditions of the power system. The results demonstrate that MIMO NSF and multivariable GPC are very effective in improving the transient power system stability and very robust against variable transmission line parameters.
Abstract: This paper investigates control methods for the 3 level unified power flow controller in order to improve the stability of a power system hence providing security under increased power flow conditions. These include a direct PI controller with decoupling (PI), Adaptive state feedback based on multivariable Elman neural network (MIMO-NSF) and multivariable GPC with decoupling algorithm (MIMO-GPC). The performances of these controllers are evaluated under different operating conditions of the power system. The results demonstrate that MIMO NSF and multivariable GPC are very effective in improving the transient power system stability and very robust against variable transmission line parameters.
[9] T. Ichikawa, K. Ichiyanagi, R. Watanabe, K. Yukita, Y. Goto, Y. Hoshino, N. Yamamoto, and S. Sugimoto, "An Estimation Method of Available Transfer Capabilities from Viewpoint of Power System Transient Stability under Deregulated Environment," Electrical Engineering in Japan, vol. 167, no. 1, pp. 66-73, Apr.2009.
Abstract: To conduct electric power transactions effectively and to operate a power system efficiently while maintaining reliability under the deregulated environment, it is required that ATC (Available Transfer Capability) be calculated at high speed and with reasonable precision. In order to address this issue, in this paper, an Artificial Neural Network-based estimation method for evaluating Maximum Transmission Capability (MTC), which is it key step but also a highly time consuming process in ATC, is proposed. It is confirmed through simulation studies that the Proposed method is capable of estimating MTC (ATC) with high speed and sufficient precision. Furthermore, the authors examined the reduction of calculation time at learning by using the transient stability index.
Abstract: To conduct electric power transactions effectively and to operate a power system efficiently while maintaining reliability under the deregulated environment, it is required that ATC (Available Transfer Capability) be calculated at high speed and with reasonable precision. In order to address this issue, in this paper, an Artificial Neural Network-based estimation method for evaluating Maximum Transmission Capability (MTC), which is it key step but also a highly time consuming process in ATC, is proposed. It is confirmed through simulation studies that the Proposed method is capable of estimating MTC (ATC) with high speed and sufficient precision. Furthermore, the authors examined the reduction of calculation time at learning by using the transient stability index.
[10] C. C. Chu, H. C. Tsai, and W. N. Chang, "Transient stability enhancement of power systems by Lyapunov-based recurrent neural networks UPFC controllers," Ieice Transactions on Fundamentals of Electronics Communications and Computer Sciences, vol. E91A, no. 9, pp. 2497-2506, Sept.2008.
Abstract: A Lyapunov-based recurrent neural networks unified power flow controller (UPFC) is developed for improving transient stability of power systems. First, a simple UPFC dynamical model, composed of a controllable shunt susceptance on the shunt side and an ideal complex transformer on the series side, is utilized to analyze UPFC dynamical characteristics. Secondly, we study the control configuration of the UPFC with two major blocks: the primary control, and the supplementary control. The primary control is implemented by standard PI techniques when the power system is operated in a normal condition. The supplementary control will be effective only when the power system is subjected by large disturbances. We propose a new Lyapunov-based UPFC controller of the classical single-machine-infinite-bus system for damping enhancement. In order to consider more complicated detailed generator models, we also propose a Lyapunov-based adaptive recurrent neural network controller to deal with such model uncertainties. This controller can be treated as neural network approximations of Lyapunov control actions. In addition, this controller also provides online learning ability to adjust the corresponding weights with the back propagation algorithm built in the hidden layer. The proposed control scheme has been tested on two simple power systems. Simulation results demonstrate that the proposed control strategy is very effective for suppressing power swing even under severe system conditions
Abstract: A Lyapunov-based recurrent neural networks unified power flow controller (UPFC) is developed for improving transient stability of power systems. First, a simple UPFC dynamical model, composed of a controllable shunt susceptance on the shunt side and an ideal complex transformer on the series side, is utilized to analyze UPFC dynamical characteristics. Secondly, we study the control configuration of the UPFC with two major blocks: the primary control, and the supplementary control. The primary control is implemented by standard PI techniques when the power system is operated in a normal condition. The supplementary control will be effective only when the power system is subjected by large disturbances. We propose a new Lyapunov-based UPFC controller of the classical single-machine-infinite-bus system for damping enhancement. In order to consider more complicated detailed generator models, we also propose a Lyapunov-based adaptive recurrent neural network controller to deal with such model uncertainties. This controller can be treated as neural network approximations of Lyapunov control actions. In addition, this controller also provides online learning ability to adjust the corresponding weights with the back propagation algorithm built in the hidden layer. The proposed control scheme has been tested on two simple power systems. Simulation results demonstrate that the proposed control strategy is very effective for suppressing power swing even under severe system conditions
[11] W. Qiao, R. G. Harley, and G. K. Venayagamoorthy, "Fault-tolerant indirect adaptive neurocontrol for a static synchronous series compensator in a power network with missing sensor measurements," Ieee Transactions on Neural Networks, vol. 19, no. 7, pp. 1179-1195, July2008.
Abstract: Identification and control of nonlinear systems depend on the availability and quality of sensor measurements. Measurements can be corrupted or interrupted due to sensor failure, broken or bad connections, bad communication, or malfunction of some hardware or software (referred to as missing sensor measurements in this paper). This paper proposes a novel fault-tolerant indirect adaptive neurocontroller (FTIANC) for controlling a static synchronous series compensator (SSSC), which is connected to a power network. The FTIANC consists of a sensor evaluation and (missing sensor) restoration scheme (SERS), a radial basis function neuroidentifier (RBFNI), and a radial basis function neurocontroller (RBFNC). The SERS provides a set of fault-tolerant measurements to the RBFNI and RBFNC. The resulting FTIANC is able to provide fault-tolerant effective control to the SSSC when some crucial time-varying sensor measurements are not available. Simulation studies are carried out on a single machine infinite bus (SMIB) as well as on the IEEE 10-machine 39-bus power system, for the SSSC equipped with conventional PI controllers (CONVC) and the FTIANC without any missing sensors, as well as for the FTIANC with multiple missing sensors. Results show that the transient performances of the proposed FTIANC with and without missing sensors are both superior to the CONVC used by the SSSC (without any missing sensors) over a wide range of system operating conditions. The proposed fault-tolerant control is readily applicable to other plant models in power systems
Abstract: Identification and control of nonlinear systems depend on the availability and quality of sensor measurements. Measurements can be corrupted or interrupted due to sensor failure, broken or bad connections, bad communication, or malfunction of some hardware or software (referred to as missing sensor measurements in this paper). This paper proposes a novel fault-tolerant indirect adaptive neurocontroller (FTIANC) for controlling a static synchronous series compensator (SSSC), which is connected to a power network. The FTIANC consists of a sensor evaluation and (missing sensor) restoration scheme (SERS), a radial basis function neuroidentifier (RBFNI), and a radial basis function neurocontroller (RBFNC). The SERS provides a set of fault-tolerant measurements to the RBFNI and RBFNC. The resulting FTIANC is able to provide fault-tolerant effective control to the SSSC when some crucial time-varying sensor measurements are not available. Simulation studies are carried out on a single machine infinite bus (SMIB) as well as on the IEEE 10-machine 39-bus power system, for the SSSC equipped with conventional PI controllers (CONVC) and the FTIANC without any missing sensors, as well as for the FTIANC with multiple missing sensors. Results show that the transient performances of the proposed FTIANC with and without missing sensors are both superior to the CONVC used by the SSSC (without any missing sensors) over a wide range of system operating conditions. The proposed fault-tolerant control is readily applicable to other plant models in power systems
[12] M. Ben Messaoud, L. Krichen, H. H. Abdallah, and A. Ouali, "Application of decentralized adaptive control on the stabilisation of multimachine power systems," International Review of Electrical Engineering-Iree, vol. 2, no. 4, pp. 489-495, July2007.
Abstract: In this paper, a decentralised adaptive control scheme for stabilisation of multimachine power systems as large-scale non-linear system is proposed In each local subsystem, the adaptive controller incorporates an appropriately additive power by designing update, law. The locally installed adaptive controllers have a simple structure and robust performance under different operation conditions and short circuit faults. The interaction signals between the different subsystems are considered as an external perturbation. This strategy does not require a priori knowledge of subsystems. The stability of the closed-loop system is proved in simulation. It is shown that all signals in the closed-loop system are bounded, and that asymptotic regulation is achieved The comparison of two control strategies- Model Reference Adaptive Control (MRAC) and PI classical control - are performed the Power Electrical System (PES). In the simulation, four power machines are considered equipped with the proposed decentralised controller. The results show that the designed strategies improve the system stability.
Abstract: In this paper, a decentralised adaptive control scheme for stabilisation of multimachine power systems as large-scale non-linear system is proposed In each local subsystem, the adaptive controller incorporates an appropriately additive power by designing update, law. The locally installed adaptive controllers have a simple structure and robust performance under different operation conditions and short circuit faults. The interaction signals between the different subsystems are considered as an external perturbation. This strategy does not require a priori knowledge of subsystems. The stability of the closed-loop system is proved in simulation. It is shown that all signals in the closed-loop system are bounded, and that asymptotic regulation is achieved The comparison of two control strategies- Model Reference Adaptive Control (MRAC) and PI classical control - are performed the Power Electrical System (PES). In the simulation, four power machines are considered equipped with the proposed decentralised controller. The results show that the designed strategies improve the system stability.
[13] A. Kahouli, T. Guesmi, H. H. Abdallah, and O. Abderrazak, "Fuzzy control approach for monomachine power systems," International Review of Electrical Engineering-Iree, vol. 2, no. 5, pp. 638-647, Sept.2007.
Abstract: Electrical power system angle stability can be improved by a wide variety of controls. Some methods have been used effectively for many years, both at generating plants and in transmission network. In this paper, a fuzzy control strategy for stabilization of the transient faulted power system is presented. The first step is to find the critical clearing time (CCT) by equal area stability criterion and numerical integration. The second interests to fuzzy logic controller. For this last step, we present the nonlinear model with a Takogi-Sugeno fuzzy model (TS). Then, a model-based in fuzzy controller design utilizing the concept of the so-called "Parallel Distributed Compensation" (PDC) is employed Stability analysis and control design problems can be reduced to linear matrix inequality (LMI) problems. Therefore, they can be solved efficiently in practice by convex programming techniques for LMI's. A single machine infinite bits system is analysed ivith the proposed methods.
Abstract: Electrical power system angle stability can be improved by a wide variety of controls. Some methods have been used effectively for many years, both at generating plants and in transmission network. In this paper, a fuzzy control strategy for stabilization of the transient faulted power system is presented. The first step is to find the critical clearing time (CCT) by equal area stability criterion and numerical integration. The second interests to fuzzy logic controller. For this last step, we present the nonlinear model with a Takogi-Sugeno fuzzy model (TS). Then, a model-based in fuzzy controller design utilizing the concept of the so-called "Parallel Distributed Compensation" (PDC) is employed Stability analysis and control design problems can be reduced to linear matrix inequality (LMI) problems. Therefore, they can be solved efficiently in practice by convex programming techniques for LMI's. A single machine infinite bits system is analysed ivith the proposed methods.
[14] A. Karami and M. S. Mohammadi, "Radial basis function neural network for power system load-flow," International Journal of Electrical Power & Energy Systems, vol. 30, no. 1, pp. 60-66, Jan.2008.
Abstract: This paper presents a method for solving the load-flow problem of the electric power systems using radial basis function (RBF) neural network with a fast hybrid training method. The main idea is that some operating conditions (values) are needed to solve the set of non-linear algebraic equations of load-flow by employing an iterative numerical technique. Therefore, we may view the outputs of a load-flow program as functions of the operating conditions. Indeed, we are faced with a function approximation problem and this can be done by an RBF neural network. The proposed approach has been successfully applied to the 10-machine and 39-bus New England test system. In addition, this method has been compared with that of a multi-layer perceptron (MLP) neural network model. The simulation results show that the RBF neural network is a simpler method to implement and requires less training time to converge than the MLP neural network.
Abstract: This paper presents a method for solving the load-flow problem of the electric power systems using radial basis function (RBF) neural network with a fast hybrid training method. The main idea is that some operating conditions (values) are needed to solve the set of non-linear algebraic equations of load-flow by employing an iterative numerical technique. Therefore, we may view the outputs of a load-flow program as functions of the operating conditions. Indeed, we are faced with a function approximation problem and this can be done by an RBF neural network. The proposed approach has been successfully applied to the 10-machine and 39-bus New England test system. In addition, this method has been compared with that of a multi-layer perceptron (MLP) neural network model. The simulation results show that the RBF neural network is a simpler method to implement and requires less training time to converge than the MLP neural network.
[15] A. Del Angel, P. Geurts, D. Ernst, M. Glavic, and L. Wehenkel, "Estimation of rotor angles of synchronous machines using artificial neural networks and local PMU-based quantities," Neurocomputing, vol. 70, no. 16-18, pp. 2668-2678, Oct.2007.
Abstract: This paper investigates a possibility for estimating rotor angles in the time frame of transient (angle) stability of electric power systems, for use in real-time. The proposed dynamic state estimation technique is based on the use of voltage and current phasors obtained from a phasor measurement unit supposed to be installed on the extra-high voltage side of the substation of a power plant, together with a multilayer perceptron trained off-line from simulations. We demonstrate that an intuitive approach to directly map phasor measurement inputs to the neural network to generator rotor angle does not offer satisfactory results. We found out that a good way to approach the angle estimation problem is to use two neural networks in order to estimate the sin(delta) and cos(delta) of the angle and recover the latter from these values by simple post-processing. Simulation results on a part of the Mexican interconnected system show that the approach could yield satisfactory accuracy for realtime monitoring and control of transient instability.
Abstract: This paper investigates a possibility for estimating rotor angles in the time frame of transient (angle) stability of electric power systems, for use in real-time. The proposed dynamic state estimation technique is based on the use of voltage and current phasors obtained from a phasor measurement unit supposed to be installed on the extra-high voltage side of the substation of a power plant, together with a multilayer perceptron trained off-line from simulations. We demonstrate that an intuitive approach to directly map phasor measurement inputs to the neural network to generator rotor angle does not offer satisfactory results. We found out that a good way to approach the angle estimation problem is to use two neural networks in order to estimate the sin(delta) and cos(delta) of the angle and recover the latter from these values by simple post-processing. Simulation results on a part of the Mexican interconnected system show that the approach could yield satisfactory accuracy for realtime monitoring and control of transient instability.
[16] W. X. Liu, J. Sarangapani, G. K. Venayagamoorthy, L. Liu, D. C. Wunsch, M. L. Crow, and D. A. Cartes, "Decentralized neural network-based excitation control of large-scale power systems," International Journal of Control Automation and Systems, vol. 5, no. 5, pp. 526-538, Oct.2007.
Abstract: This paper presents a neural network based decentralized excitation controller design for large-scale power systems. The proposed controller design considers not only the dynamics of generators but also the algebraic constraints of the power flow equations. The control signals are calculated using only local signals. The transient stability and the coordination of the subsystem control activities are guaranteed through rigorous stability analysis. Neural networks in the controller design are used to approximate the unknown/imprecise dynamics of the local power system and the interconnections. All signals in the closed loop system are guaranteed to be uniformly ultimately bounded. To evaluate its performance, the proposed controller design is compared with conventional controllers optimized using particle swarm optimization. Simulations with a three-machine power system under different disturbances demonstrate the effectiveness of the proposed controller design
Abstract: This paper presents a neural network based decentralized excitation controller design for large-scale power systems. The proposed controller design considers not only the dynamics of generators but also the algebraic constraints of the power flow equations. The control signals are calculated using only local signals. The transient stability and the coordination of the subsystem control activities are guaranteed through rigorous stability analysis. Neural networks in the controller design are used to approximate the unknown/imprecise dynamics of the local power system and the interconnections. All signals in the closed loop system are guaranteed to be uniformly ultimately bounded. To evaluate its performance, the proposed controller design is compared with conventional controllers optimized using particle swarm optimization. Simulations with a three-machine power system under different disturbances demonstrate the effectiveness of the proposed controller design
[17] N. Amjady and S. F. Majedi, "Transient stability prediction by a hybrid intelligent system," Ieee Transactions on Power Systems, vol. 22, no. 3, pp. 1275-1283, Aug.2007.
Abstract: In this paper, a new hybrid intelligent system is proposed for transient stability prediction. This intelligent system is composed of a preprocessor, an array of neural networks (NN) and an interpreter. The preprocessor partitions the whole set of synchronous machines into subsets, each one including only two generators. Each subset is assigned to one NN, which extracts the input/output mapping function of that subset. Then, the interpreter combines the responses of the NNs in a voting procedure to determine the transient stability status of the power system. This mechanism can cover the probable errors of the NNs, increasing the accuracy of the final response of the hybrid intelligent system. In addition to the transient stability status, this intelligent system can determine tripped generators and islanded parts of the power system for unstable cases. The proposed method has been examined on the PSB4 and New England test systems. The obtained results indicate the efficiency of the hybrid intelligent system for transient stability prediction
Abstract: In this paper, a new hybrid intelligent system is proposed for transient stability prediction. This intelligent system is composed of a preprocessor, an array of neural networks (NN) and an interpreter. The preprocessor partitions the whole set of synchronous machines into subsets, each one including only two generators. Each subset is assigned to one NN, which extracts the input/output mapping function of that subset. Then, the interpreter combines the responses of the NNs in a voting procedure to determine the transient stability status of the power system. This mechanism can cover the probable errors of the NNs, increasing the accuracy of the final response of the hybrid intelligent system. In addition to the transient stability status, this intelligent system can determine tripped generators and islanded parts of the power system for unstable cases. The proposed method has been examined on the PSB4 and New England test systems. The obtained results indicate the efficiency of the hybrid intelligent system for transient stability prediction
[18] A. D. P. Lotufo, M. L. M. Lopes, and C. R. Minussi, "Sensitivity analysis by neural networks applied to power systems transient stability," Electric Power Systems Research, vol. 77, no. 7, pp. 730-738, May2007.
Abstract: This work presents a procedure for transient stability analysis and preventive control of electric power systems, which is formulated by a multilayer feedforward neural network. The neural network training is realized by using the back-propagation algorithm with fuzzy controller and adaptation of the inclination and translation parameters of the nonlinear function. These procedures provide a faster convergence and more precise results, if compared to the traditional back-propagation algorithm. The adaptation of the training rate is effectuated by using the information of the global error and global error variation. After finishing the training, the neural network is capable of estimating the security margin and the sensitivity analysis. Considering this information, it is possible to develop a method for the realization of the security correction (preventive control) for levels considered appropriate to the system, based on generation reallocation and load shedding. An application for a multimachine power system is presented to illustrate the proposed methodology.
Abstract: This work presents a procedure for transient stability analysis and preventive control of electric power systems, which is formulated by a multilayer feedforward neural network. The neural network training is realized by using the back-propagation algorithm with fuzzy controller and adaptation of the inclination and translation parameters of the nonlinear function. These procedures provide a faster convergence and more precise results, if compared to the traditional back-propagation algorithm. The adaptation of the training rate is effectuated by using the information of the global error and global error variation. After finishing the training, the neural network is capable of estimating the security margin and the sensitivity analysis. Considering this information, it is possible to develop a method for the realization of the security correction (preventive control) for levels considered appropriate to the system, based on generation reallocation and load shedding. An application for a multimachine power system is presented to illustrate the proposed methodology.
[19] H. H. Abdallah, M. Chtourou, T. Guesmi, and A. Ouali, "Feedforward neural network-based transient stability analysis of electric power systems," European Transactions on Electrical Power, vol. 16, no. 6, pp. 577-590, Nov.2006.
Abstract: This paper presents a neural approach for the transient stability analysis of electric power systems (EPS). The transient stability of an EPS expresses the ability of the system to preserve synchronism after sudden severe disturbances. Its analysis needs the computation of the critical clearing time (CCT), which determines the security degree of the system. The classical methods for the determination of the CCT are computation time consuming and may be not treatable in real time. A feedforward neural network trained off-line using an historical database can approximate the simulation studies to give in real time an accurate estimate of the CCT. The identified neural network can be updated using new significant data to learn more disturbance cases.
Abstract: This paper presents a neural approach for the transient stability analysis of electric power systems (EPS). The transient stability of an EPS expresses the ability of the system to preserve synchronism after sudden severe disturbances. Its analysis needs the computation of the critical clearing time (CCT), which determines the security degree of the system. The classical methods for the determination of the CCT are computation time consuming and may be not treatable in real time. A feedforward neural network trained off-line using an historical database can approximate the simulation studies to give in real time an accurate estimate of the CCT. The identified neural network can be updated using new significant data to learn more disturbance cases.
[20] A. Demiroren, H. L. Zeynelgil, and S. N. Sengor, "The application of neural network controller to power system with SMES for transient stability enhancement," European Transactions on Electrical Power, vol. 16, no. 6, pp. 629-646, Nov.2006.
Abstract: In this paper, a synchronous generator including power system stabilizer (PSS), voltage regulator, and governor is considered. This generator also has a superconducting magnetic energy storage (SMES) unit at its terminal bus. The investigation of the transient stability enhancement for the whole system is done using SMES unit and neural network (NN) controllers, while one of the controllers affects the mechanical input; the other affects the exciter input. Thus, non-linear power system control is provided by a control application of layered neural networks. The back propagation-through-time algorithm is used as a control rule for the NN controller.
Abstract: In this paper, a synchronous generator including power system stabilizer (PSS), voltage regulator, and governor is considered. This generator also has a superconducting magnetic energy storage (SMES) unit at its terminal bus. The investigation of the transient stability enhancement for the whole system is done using SMES unit and neural network (NN) controllers, while one of the controllers affects the mechanical input; the other affects the exciter input. Thus, non-linear power system control is provided by a control application of layered neural networks. The back propagation-through-time algorithm is used as a control rule for the NN controller.
[21] H. Sawhney and B. Jeyasurya, "A feed-forward artificial neural network with enhanced feature selection for power system transient stability assessment," Electric Power Systems Research, vol. 76, no. 12, pp. 1047-1054, Aug.2006.
Abstract: This paper describes an approach where an artificial neural network is used to predict the stability status of the power system. This efficient and robust approach combines the advantages of the time-domain integration schemes and artificial neural network for on-line transient stability assessment of the power system. The transient stability index has been obtained by the extended equal area criterion method and is used as an output of the neural network. Two feature selection techniques have been used to identify the input variables best suitable for training. The proposed technique predicts the transient stability index correctly, without any false alarm. In addition, the transient stability index as an output of the neural network helps to implement possible control actions. The results obtained demonstrate the potential for neural network to be a part of any on-line dynamic security assessment tool.
Abstract: This paper describes an approach where an artificial neural network is used to predict the stability status of the power system. This efficient and robust approach combines the advantages of the time-domain integration schemes and artificial neural network for on-line transient stability assessment of the power system. The transient stability index has been obtained by the extended equal area criterion method and is used as an output of the neural network. Two feature selection techniques have been used to identify the input variables best suitable for training. The proposed technique predicts the transient stability index correctly, without any false alarm. In addition, the transient stability index as an output of the neural network helps to implement possible control actions. The results obtained demonstrate the potential for neural network to be a part of any on-line dynamic security assessment tool.
[22] S. Mishra, "Neural-network-based adaptive UPFC for improving transient stability performance of power system," Ieee Transactions on Neural Networks, vol. 17, no. 2, pp. 461-470, Mar.2006.
Abstract: This paper uses the recently proposed H-infinity-learning method, for updating the parameter of the radial basis function neural network (RBFNN) used as a control scheme for the unified power flow controller (UPFC) to improve the transient stability performance of a multimachine power system. The RBFNN uses a single neuron architecture whose input is proportional to the difference in error and the updating of its parameters is carried via a proportional value of the error. Also, the coefficients of the difference of error, error, and auxiliary signal used for improving damping performance are depicted by a genetic algorithm. The performance of the newly designed controller is evaluated in a four-machine power system subjected to different types of disturbances. The newly designed single-neuron RBFNN-based UPFC exhibits better damping performance compared to the conventional PIID as well as the extended Kalman filter (EKF) updating-based RBFNN scheme, making the unstable cases stable. Its simple architecture reduces the computational burden, thereby making it attractive for real-time implementation. Also, all the machines are being equipped with the conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system
Abstract: This paper uses the recently proposed H-infinity-learning method, for updating the parameter of the radial basis function neural network (RBFNN) used as a control scheme for the unified power flow controller (UPFC) to improve the transient stability performance of a multimachine power system. The RBFNN uses a single neuron architecture whose input is proportional to the difference in error and the updating of its parameters is carried via a proportional value of the error. Also, the coefficients of the difference of error, error, and auxiliary signal used for improving damping performance are depicted by a genetic algorithm. The performance of the newly designed controller is evaluated in a four-machine power system subjected to different types of disturbances. The newly designed single-neuron RBFNN-based UPFC exhibits better damping performance compared to the conventional PIID as well as the extended Kalman filter (EKF) updating-based RBFNN scheme, making the unstable cases stable. Its simple architecture reduces the computational burden, thereby making it attractive for real-time implementation. Also, all the machines are being equipped with the conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system
[23] W. P. Ferreira, M. D. G. Silveira, A. D. P. Lotufo, and C. R. Minussi, "Transient stability analysis of electric energy systems via a fuzzy ART-ARTMAP neural network," Electric Power Systems Research, vol. 76, no. 6-7, pp. 466-475, Apr.2006.
Abstract: This work presents a methodology to analyze transient stability (first oscillation) of electric energy systems, using a neural network based on ART architecture (adaptive resonance theory), named fuzzy ART-ARTMAP neural network for real time applications. The security margin is used as a stability analysis criterion, considering three-phase short circuit faults with a transmission line outage. The neural network operation consists of two fundamental phases: the training and the analysis. The training phase needs a great quantity of processing for the realization, while the analysis phase is effectuated almost without computation effort. This is, therefore the principal purpose to use neural networks for solving complex problems that need fast solutions, as the applications in real time. The ART neural networks have as primordial characteristics the plasticity and the stability, which are essential qualities to the training execution and to an efficient analysis. The fuzzy ART-ARTMAP neural network is proposed seeking a superior performance, in terms of precision and speed, when compared to conventional ARTMAP, and much more when compared to the neural networks that use the training by backpropagation algorithm, which is a benchmark in neural network area.
Abstract: This work presents a methodology to analyze transient stability (first oscillation) of electric energy systems, using a neural network based on ART architecture (adaptive resonance theory), named fuzzy ART-ARTMAP neural network for real time applications. The security margin is used as a stability analysis criterion, considering three-phase short circuit faults with a transmission line outage. The neural network operation consists of two fundamental phases: the training and the analysis. The training phase needs a great quantity of processing for the realization, while the analysis phase is effectuated almost without computation effort. This is, therefore the principal purpose to use neural networks for solving complex problems that need fast solutions, as the applications in real time. The ART neural networks have as primordial characteristics the plasticity and the stability, which are essential qualities to the training execution and to an efficient analysis. The fuzzy ART-ARTMAP neural network is proposed seeking a superior performance, in terms of precision and speed, when compared to conventional ARTMAP, and much more when compared to the neural networks that use the training by backpropagation algorithm, which is a benchmark in neural network area.
[24] P. Vera-Candeas, N. Ruiz-Reyes, and F. Jurado, "Transient voltage stability and voltage sag discrimination by matching pursuit-based transient modeling and neural networks," Electric Power Components and Systems, vol. 34, no. 3, pp. 321-341, Mar.2006.
Abstract: This article presents a method to discriminate between transient voltage stability and voltage sag. Transient modeling based on matching pursuit with an overcomplete dictionary of wavelet functions is a powerful tool in the analysis of the transient phenomena in power systems because of its ability to accurately represent them in both time and frequency domains with a minimum amount of information. This is a desirable feature when looking for accuracy and computational cost, as discrimination is performed by combining the information provided by the signal analysis tool with a neural network. In our approach, the information provided by the matching pursuitbased transient modeling stage is applied to train a neural network in a fast and accurate fashion. The simulated results presented clearly show that the proposed technique can discriminate accurately between transient voltage stability and voltage sag in power system protection with low computation cost
Abstract: This article presents a method to discriminate between transient voltage stability and voltage sag. Transient modeling based on matching pursuit with an overcomplete dictionary of wavelet functions is a powerful tool in the analysis of the transient phenomena in power systems because of its ability to accurately represent them in both time and frequency domains with a minimum amount of information. This is a desirable feature when looking for accuracy and computational cost, as discrimination is performed by combining the information provided by the signal analysis tool with a neural network. In our approach, the information provided by the matching pursuitbased transient modeling stage is applied to train a neural network in a fast and accurate fashion. The simulated results presented clearly show that the proposed technique can discriminate accurately between transient voltage stability and voltage sag in power system protection with low computation cost
[25] M. H. Wang and H. C. Chen, "Transient stability control of multimachine power systems using flywheel energy injection," Iee Proceedings-Generation Transmission and Distribution, vol. 152, no. 5, pp. 589-596, Sept.2005.
Abstract: Owing to advances in many technologies, the high-speed flywheel energy storage system (FESS), flywheel battery, has become a viable alternative to electrochemical batteries and attracted much research attention in recent years. A self-organising fuzzy neural network controller is presented for FESS to improve transient stability and increase transfer capability of power systems. The main difference from a traditional control approach ties in the model-free description of the control system and parallel computing capability. Simulation results from the Taiwan power system (Taipower) show that FESS with the proposed controller has produced significant improvement in power system performance
Abstract: Owing to advances in many technologies, the high-speed flywheel energy storage system (FESS), flywheel battery, has become a viable alternative to electrochemical batteries and attracted much research attention in recent years. A self-organising fuzzy neural network controller is presented for FESS to improve transient stability and increase transfer capability of power systems. The main difference from a traditional control approach ties in the model-free description of the control system and parallel computing capability. Simulation results from the Taiwan power system (Taipower) show that FESS with the proposed controller has produced significant improvement in power system performance
[26] N. Ruiz-Reyes, P. Vera-Candeas, and F. Jurado, "Discrimination between transient voltage stability and voltage sag using damped sinusoids-based transient modeling," Ieee Transactions on Power Delivery, vol. 20, no. 4, pp. 2644-2650, Oct.2005.
Abstract: This paper presents a technique for accurate discrimination between transient voltage stability and voltage sag by combining damped sinusoids-based transient modeling with neural networks. Transient modeling is accomplished by energy adapted matching pursuits with an over-complete dictionary of damped sinusoids. In our approach, the information provided by the damped sinusoids-based transient modeling stage is applied to a Neural Network, which determine in a fast and accurate fashion the class to which the waveform belongs. The simulated results clearly show that the, proposed technique can accurately discriminate between transient voltage stability and voltage sag in power system protection
Abstract: This paper presents a technique for accurate discrimination between transient voltage stability and voltage sag by combining damped sinusoids-based transient modeling with neural networks. Transient modeling is accomplished by energy adapted matching pursuits with an over-complete dictionary of damped sinusoids. In our approach, the information provided by the damped sinusoids-based transient modeling stage is applied to a Neural Network, which determine in a fast and accurate fashion the class to which the waveform belongs. The simulated results clearly show that the, proposed technique can accurately discriminate between transient voltage stability and voltage sag in power system protection
[27] Y. P. Fan, Y. P. Chen, W. S. Sun, D. Liu, and Y. Chai, "Contingency screening of power system based on rough sets and fuzzy ARTMAP," Advances in Neural Networks - Isnn 2005, Pt 3, Proceedings, vol. 3498, pp. 654-661, 2005.
Abstract: The paper adopts rough sets theory and fuzzy ARTMAP method to explore the online adaptive contingency classification in power system transient stability control. On the basis of contingency vector space model, the rough sets theory is applied to generalize the information system comprised by contingency samples set, and compute the best reducing properties set. So dimension of contingency feature space is reduced greatly, and disturbance in contingency classification is decreased too, which improves the efficiency of classification. In addition, using the advantage of adaptive classification and incremental learning of Fuzzy ARTMAP neural network, the online adaptive classification of contingency is achieved
Abstract: The paper adopts rough sets theory and fuzzy ARTMAP method to explore the online adaptive contingency classification in power system transient stability control. On the basis of contingency vector space model, the rough sets theory is applied to generalize the information system comprised by contingency samples set, and compute the best reducing properties set. So dimension of contingency feature space is reduced greatly, and disturbance in contingency classification is decreased too, which improves the efficiency of classification. In addition, using the advantage of adaptive classification and incremental learning of Fuzzy ARTMAP neural network, the online adaptive classification of contingency is achieved
[28] M. Jalili-Kharaajoo and R. Mohammadi-Millasi, "Design of simple neuro-controller for global transient control and voltage regulation of power systems," International Journal of Control Automation and Systems, vol. 3, no. 2, pp. 302-307, June2005.
Abstract: A novel neuro controller based simple neuro-structure with modified error function is introduced in this paper. This controller consists of two independent controllers, known as the voltage regulator and the angular controller. The voltage regulator is used to modify terminal voltage for the purpose of tracking a reference voltage. The angular controller is utilized to guarantee the stability of the system. In this structure each neuron uses a linear hard limit activation function that depends on the controlled variable and its derivatives. There is no need for parameter identification or any off-line training data. Two proposed controllers are merged by a smooth switch to build a complete controller. The effectiveness of the proposed novel control action is demonstrated through some computer simulations on a Single-Machine Infinite-Bus (SMIB) power system
Abstract: A novel neuro controller based simple neuro-structure with modified error function is introduced in this paper. This controller consists of two independent controllers, known as the voltage regulator and the angular controller. The voltage regulator is used to modify terminal voltage for the purpose of tracking a reference voltage. The angular controller is utilized to guarantee the stability of the system. In this structure each neuron uses a linear hard limit activation function that depends on the controlled variable and its derivatives. There is no need for parameter identification or any off-line training data. Two proposed controllers are merged by a smooth switch to build a complete controller. The effectiveness of the proposed novel control action is demonstrated through some computer simulations on a Single-Machine Infinite-Bus (SMIB) power system
[29] M. H. Wang, "Application of flywheel energy storage system to enhance transient stability of power systems," Electric Power Components and Systems, vol. 33, no. 4, pp. 463-479, Apr.2005.
Abstract: This article aims to develop a self-organizing control scheme for the flywheel energy storage system (FESS) to enhance transient stability of power systems. Due to the model of transient stability control being a nonlinear dynamic equation, a self-organizing neural network-based fuzzy controller is introduced to implement in the FESS control system. The membership functions and control rules of fuzzy controller are expressed as the processing nodes in the neural network (NN). Then, the heuristic fuzzy control parameters can be optimally tuned from training examples due to excellent organizing capability of NN. For robustness consideration, a multilayer neural network is used to learn the relation of operation conditions and optimal parameters of the controller To demonstrate the effectiveness of the proposed controller some simulations are conducted on a single-machine-infinite-bus (SMIB) power system. The results show that the FESS with the proposed controller has produced significant improvement in the power system stability
Abstract: This article aims to develop a self-organizing control scheme for the flywheel energy storage system (FESS) to enhance transient stability of power systems. Due to the model of transient stability control being a nonlinear dynamic equation, a self-organizing neural network-based fuzzy controller is introduced to implement in the FESS control system. The membership functions and control rules of fuzzy controller are expressed as the processing nodes in the neural network (NN). Then, the heuristic fuzzy control parameters can be optimally tuned from training examples due to excellent organizing capability of NN. For robustness consideration, a multilayer neural network is used to learn the relation of operation conditions and optimal parameters of the controller To demonstrate the effectiveness of the proposed controller some simulations are conducted on a single-machine-infinite-bus (SMIB) power system. The results show that the FESS with the proposed controller has produced significant improvement in the power system stability
[30] S. Mishra, "Hybrid-neuro-fuzzy UPFC for improving transient stability performance of power system," Electric Power Components and Systems, vol. 33, no. 1, pp. 73-84, Jan.2005.
Abstract: This article presents a new technique of combining the advantages of both conventional proportional and integral (PI) controller with a radial basis function neural network (RBFNN) with Takagi-Sugeno (TS) fuzzy updating of its parameters. The error is given as input to the RBFNN, which in turn outputs a modified error to be used by the PI controller. This control scheme is used for controlling the series voltage injection through unified power flow controller (UPFC) to improve the modal oscillations of a multi-machine power system. Further, a new local auxiliary signal derived from phase angle difference across the UPFC series transformer is added to the real power error to improve the damping performance. This eliminates the need of generator speed mostly used for improving modal oscillation damping. Besides, all the machines are being equipped with conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system. Digital simulation of a four machine power system subjected to a wide variety of disturbances validates the efficiency of the new approach
Abstract: This article presents a new technique of combining the advantages of both conventional proportional and integral (PI) controller with a radial basis function neural network (RBFNN) with Takagi-Sugeno (TS) fuzzy updating of its parameters. The error is given as input to the RBFNN, which in turn outputs a modified error to be used by the PI controller. This control scheme is used for controlling the series voltage injection through unified power flow controller (UPFC) to improve the modal oscillations of a multi-machine power system. Further, a new local auxiliary signal derived from phase angle difference across the UPFC series transformer is added to the real power error to improve the damping performance. This eliminates the need of generator speed mostly used for improving modal oscillation damping. Besides, all the machines are being equipped with conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system. Digital simulation of a four machine power system subjected to a wide variety of disturbances validates the efficiency of the new approach
[31] Y. T. Liu, X. D. Chu, Y. Y. Sun, and L. Li, "Transient stability assessment using radial basis function networks," Advances in Neural Networks - Isnn 2004, Pt 2, vol. 3174, pp. 581-586, 2004.
Abstract: A practical approach is proposed to power system transient stability assessment by monitoring and controlling active power flow on critical transmission lines. A radial basis function network is trained to estimate transient stability limit of active power flow on a critical line. Once the transient stability limit is violated, a preventive control decision is made in terms of generation rescheduling. Control amount is determined using first-order sensitivities of transient stability margin with respect to generator outputs, which can be derived directly from partial derivatives of the trained radial basis function network's output to inputs. Simulation results of a real-world power system demonstrate the effectiveness of the proposed approach
Abstract: A practical approach is proposed to power system transient stability assessment by monitoring and controlling active power flow on critical transmission lines. A radial basis function network is trained to estimate transient stability limit of active power flow on a critical line. Once the transient stability limit is violated, a preventive control decision is made in terms of generation rescheduling. Control amount is determined using first-order sensitivities of transient stability margin with respect to generator outputs, which can be derived directly from partial derivatives of the trained radial basis function network's output to inputs. Simulation results of a real-world power system demonstrate the effectiveness of the proposed approach
[32] N. Amjady, "A framework of reliability assessment with consideration effect of transient and voltage stabilities," Ieee Transactions on Power Systems, vol. 19, no. 2, pp. 1005-1014, May2004.
Abstract: With increased energy demand, less new transmission, and open access, the power system is experiencing a much greater level of power transfer. These new requirements push the system to its limits for maximum economic benefit, while maintaining sufficient security margins that require online network analysis. A practical interconnected system can collapse due to a number of different limits being exceeded such as thermal, transient stability, and voltage stability. This paper provides a novel framework for extending conventional probabilistic reliability analysis to account for system stability limits. The proposed method includes transient and voltage stability issues in the adequacy assessment of a composite system. The main component of the method is an intelligent system, which is used to modify reliability indexes due to stability considerations. The intelligent system is a combination of neural network and fuzzy neural network. The method is examined on a practical case study
Abstract: With increased energy demand, less new transmission, and open access, the power system is experiencing a much greater level of power transfer. These new requirements push the system to its limits for maximum economic benefit, while maintaining sufficient security margins that require online network analysis. A practical interconnected system can collapse due to a number of different limits being exceeded such as thermal, transient stability, and voltage stability. This paper provides a novel framework for extending conventional probabilistic reliability analysis to account for system stability limits. The proposed method includes transient and voltage stability issues in the adequacy assessment of a composite system. The main component of the method is an intelligent system, which is used to modify reliability indexes due to stability considerations. The intelligent system is a combination of neural network and fuzzy neural network. The method is examined on a practical case study
[33] A. G. Bahbah and A. A. Girgis, "New method for generators' angles and angular velocities prediction for transient stability assessment of multimachine power systems using recurrent artificial neural network," Ieee Transactions on Power Systems, vol. 19, no. 2, pp. 1015-1022, May2004.
Abstract: Recurrent radial basis function (RBF) and multilayer perceptron (MLP) artificial neural network (ANN) schemes are proposed for dynamic system modeling, and generators' angles and angular velocities prediction for transient stability assessment. The method is presented for multimachine power systems. In this scheme, transient stability is assessed based on monitoring generators' angles and angular velocities with time, and checking whether they exceed the specified limits for system stability or not. Data generation schemes have been proposed. The proposed recurrent ANN scheme is not sensitive to fault locations. It is only dependent on the postfault system configuration
Abstract: Recurrent radial basis function (RBF) and multilayer perceptron (MLP) artificial neural network (ANN) schemes are proposed for dynamic system modeling, and generators' angles and angular velocities prediction for transient stability assessment. The method is presented for multimachine power systems. In this scheme, transient stability is assessed based on monitoring generators' angles and angular velocities with time, and checking whether they exceed the specified limits for system stability or not. Data generation schemes have been proposed. The proposed recurrent ANN scheme is not sensitive to fault locations. It is only dependent on the postfault system configuration
[34] R. J. Wai and H. H. Chang, "Backstepping wavelet neural network control for indirect field-oriented induction motor drive," Ieee Transactions on Neural Networks, vol. 15, no. 2, pp. 367-382, Mar.2004.
Abstract: This study address a newly designed decoupling system and a backstepping wavelet neural network (WNN) control system for achieving high-precision position-tracking performance of an indirect field-oriented induction motor (IM) drive. First, a decoupling mechanism with an online inverse time-constant estimation algorithm is derived on the basis of model reference adaptive system theory to preserve the decoupling control characteristic of an indirect field-oriented IM drive. Moreover, based on the backstepping design methodology, a desired feedback control law is developed for ensuring the favorable control performance. However, the uncertainties, such as mechanical parameter uncertainty, external load disturbance, unstructured uncertainty due to nonideal field orientation in transient state, and unmodeled dynamics in practical applications, are difficult to know in advance. Thus, the stability of the desired feedback control may be destroyed. Due to the powerful approximation ability of WNN, a backstepping WNN control scheme is designed in this study to control the rotor position of an indirect field-oriented IM drive for periodic motion. This control scheme contains two parts: one is a WNN control that is utilized to mimic the desired feedback control law, and the other is a robust control that is designed to recover the residual part of approximation for ensuring the stable control characteristic. In addition, numerical simulation and experimental results due to periodic commands are provided to verify the effectiveness of the proposed control strategy
Abstract: This study address a newly designed decoupling system and a backstepping wavelet neural network (WNN) control system for achieving high-precision position-tracking performance of an indirect field-oriented induction motor (IM) drive. First, a decoupling mechanism with an online inverse time-constant estimation algorithm is derived on the basis of model reference adaptive system theory to preserve the decoupling control characteristic of an indirect field-oriented IM drive. Moreover, based on the backstepping design methodology, a desired feedback control law is developed for ensuring the favorable control performance. However, the uncertainties, such as mechanical parameter uncertainty, external load disturbance, unstructured uncertainty due to nonideal field orientation in transient state, and unmodeled dynamics in practical applications, are difficult to know in advance. Thus, the stability of the desired feedback control may be destroyed. Due to the powerful approximation ability of WNN, a backstepping WNN control scheme is designed in this study to control the rotor position of an indirect field-oriented IM drive for periodic motion. This control scheme contains two parts: one is a WNN control that is utilized to mimic the desired feedback control law, and the other is a robust control that is designed to recover the residual part of approximation for ensuring the stable control characteristic. In addition, numerical simulation and experimental results due to periodic commands are provided to verify the effectiveness of the proposed control strategy
[35] J. W. Park, R. G. Harley, and G. K. Venayagamoorthy, "Indirect adaptive control for synchronous generator: Comparison of MLP/RBF neural networks approach with Lyapunov stability analysis," Ieee Transactions on Neural Networks, vol. 15, no. 2, pp. 460-464, Mar.2004.
Abstract: This paper compares two indirect adaptive neurocontrollers, namely a multilayer perceptron neurocontroller (MLPNC) and a radial basis function neurocontroller (RBFNC) to control a synchronous generator. The different damping and transient performances of two neurocontrollers are compared with those of conventional linear controllers, and analyzed based on the Lyapunov direct method
Abstract: This paper compares two indirect adaptive neurocontrollers, namely a multilayer perceptron neurocontroller (MLPNC) and a radial basis function neurocontroller (RBFNC) to control a synchronous generator. The different damping and transient performances of two neurocontrollers are compared with those of conventional linear controllers, and analyzed based on the Lyapunov direct method
[36] Y. T. Liu and X. D. Chu, "Determination of generator-tripping and load-shedding by compound neural network," Engineering Intelligent Systems for Electrical Engineering and Communications, vol. 12, no. 1, pp. 29-34, Mar.2004.
Abstract: A Compound neural network is proposed to coordinate the, first swing stability control decision of generator-tripping and load-shedding in multi-machine power system in this paper. The stability classification part consists of a fuzzy clustering network and several radial basis function networks, and the load-shedding decision part is composed of a fuzzy clustering, network and back-propagation networks. The direct generator rotor angle measurements are simply computed as inputs of the compound neural network. Taking advantages of different kinds of algorithms for neural networks, a training procedure for the compound neural network is presented. Simulation results of a practical power system demonstrate that the classification accuracy and decision precision are quite high
Abstract: A Compound neural network is proposed to coordinate the, first swing stability control decision of generator-tripping and load-shedding in multi-machine power system in this paper. The stability classification part consists of a fuzzy clustering network and several radial basis function networks, and the load-shedding decision part is composed of a fuzzy clustering, network and back-propagation networks. The direct generator rotor angle measurements are simply computed as inputs of the compound neural network. Taking advantages of different kinds of algorithms for neural networks, a training procedure for the compound neural network is presented. Simulation results of a practical power system demonstrate that the classification accuracy and decision precision are quite high
[37] K. R. Niazi, C. M. Arora, and S. L. Surana, "Power system security evaluation using ANN: feature selection using divergence," Electric Power Systems Research, vol. 69, no. 2-3, pp. 161-167, May2004.
Abstract: This paper presents an artificial neural network (ANN)-based method for on-line security evaluation of power systems. One of the important considerations in applying ANN is feature selection. A new divergence-based feature selection algorithm has been proposed and investigated. The method has been applied on an IEEE test system and the results demonstrate the suitability of the proposed method for on-line security evaluation of power systems even under changing topological conditions.
Abstract: This paper presents an artificial neural network (ANN)-based method for on-line security evaluation of power systems. One of the important considerations in applying ANN is feature selection. A new divergence-based feature selection algorithm has been proposed and investigated. The method has been applied on an IEEE test system and the results demonstrate the suitability of the proposed method for on-line security evaluation of power systems even under changing topological conditions.
[38] N. Amjady, "Dynamic voltage security assessment by a neural network based method," Electric Power Systems Research, vol. 66, no. 3, pp. 215-226, Sept.2003.
Abstract: The voltage security problem is an indispensable aspect of power system security. Voltage stability limits constrain the loading capabilities of power systems. In recent years, some papers have shown that voltage stability is a dynamic problem. In practice static analysis methods, like power flow based methods, may have deficiency to evaluate voltage stability or voltage security problems. On the other hand, dynamic modeling and evaluation of voltage stability problem are complex, expensive and time consuming. In this paper. a neural network (NN) approach has been presented for this purpose. This NN can establish a mapping between operating conditions and dynamic voltage stability margin (VSM) of each bus. This analysis gives an insight about robustness of different buses and dynamic voltage security status of power system. The method has been examined on a portion of Iran's south-west transmission network. Obtained results confirm the validity of the developed approach.
Abstract: The voltage security problem is an indispensable aspect of power system security. Voltage stability limits constrain the loading capabilities of power systems. In recent years, some papers have shown that voltage stability is a dynamic problem. In practice static analysis methods, like power flow based methods, may have deficiency to evaluate voltage stability or voltage security problems. On the other hand, dynamic modeling and evaluation of voltage stability problem are complex, expensive and time consuming. In this paper. a neural network (NN) approach has been presented for this purpose. This NN can establish a mapping between operating conditions and dynamic voltage stability margin (VSM) of each bus. This analysis gives an insight about robustness of different buses and dynamic voltage security status of power system. The method has been examined on a portion of Iran's south-west transmission network. Obtained results confirm the validity of the developed approach.
[39] T. Senjyu, Y. Morishima, T. Yamashita, K. Uezato, and H. Fujita, "Recurrent neural network supplementary stabilization controller for automatic voltage regulator and governor," Electric Power Components and Systems, vol. 31, no. 7, pp. 693-707, July2003.
Abstract: Excitation controllers such as automatic voltage regulators (AVRs) and power system stabilizers (PSSs) are normally installed on synchronous generators for improving electric power systems' transient stability. The PSS optimized by the genetic algorithm (GA) has a certain robustness. However, since the power system is nonlinear, drastic changes in the system caused by faults and circuit switching may cause control performance to become unsatisfactory. Then a method using a nonlinear neural network can be used to tune the control systems. This method of using neural networks has been reported in recent years. This paper presents a recurrent neural network (RNN) stabilization controller to improve the transient stability of power systems. The proposed controller is constructed by a three-layer (8-9-1) RNN, of which inputs are DeltaP(e) and Deltaomega. The weights of the proposed controller are adjusted online to maintain electrical output power deviation equal to zero. By applying the proposed controller, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed controller has been investigated in a single-machine infinite-bus system
Abstract: Excitation controllers such as automatic voltage regulators (AVRs) and power system stabilizers (PSSs) are normally installed on synchronous generators for improving electric power systems' transient stability. The PSS optimized by the genetic algorithm (GA) has a certain robustness. However, since the power system is nonlinear, drastic changes in the system caused by faults and circuit switching may cause control performance to become unsatisfactory. Then a method using a nonlinear neural network can be used to tune the control systems. This method of using neural networks has been reported in recent years. This paper presents a recurrent neural network (RNN) stabilization controller to improve the transient stability of power systems. The proposed controller is constructed by a three-layer (8-9-1) RNN, of which inputs are DeltaP(e) and Deltaomega. The weights of the proposed controller are adjusted online to maintain electrical output power deviation equal to zero. By applying the proposed controller, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed controller has been investigated in a single-machine infinite-bus system
[40] Y. Tang, H. Chen, H. F. Wang, R. Aggarwal, A. T. Johns, X. Z. Dai, and N. H. Li, "Implementation and test of a TCSC ANN-based alpha th order inverse control system," International Journal of Electrical Power & Energy Systems, vol. 25, no. 4, pp. 309-317, May2003.
Abstract: This paper presents the laboratory implementation and test results of an advanced TCSC ANN-based alphath order inverse control system to enhance power system transient stability. Satisfactory performance and robustness of the TCSC control are demonstrated by the test results on a laboratory power system subject to different disturbances under various operating conditions.
Abstract: This paper presents the laboratory implementation and test results of an advanced TCSC ANN-based alphath order inverse control system to enhance power system transient stability. Satisfactory performance and robustness of the TCSC control are demonstrated by the test results on a laboratory power system subject to different disturbances under various operating conditions.
[41] S. Mishra, P. K. Dash, P. K. Hota, and M. Tripathy, "Genetically optimized neuro-fuzzy IPFC for damping modal oscillations of power system," Ieee Transactions on Power Systems, vol. 17, no. 4, pp. 1140-1147, Nov.2002.
Abstract: An integrated approach of radial basis function neural network (RBFNN) and Takagi-Sugeno (TS) fuzzy scheme with a genetic optimization of their parameters has been developed in this paper to design intelligent adaptive controllers for improving the transient stability performance of power systems. At the outset, this concept is applied to a simple device such as thyristor-controlled series capacitor (TCSC) connected in a single-machine infinite bus power system and is then extended to interline power-flow controller (IPFC) connected in a multimachine power system. The RBFNN uses single neuron architecture and its parameters are dynamically updated in an online fashion with TS-fuzzy scheme designed with only four rules and triangular membership function. The rules of the TS-fuzzy scheme are derived from the real- or reactive-power error and their derivatives either at the TCSC or IPFC buses depending on the device. Further, to implement this combined scheme only one coefficient in the TS-fuzzy rules needs to be optimized. The optimization of this coefficient as well as the coefficient for auxiliary signal generation is performed through genetic algorithm. The performance of the new controller is evaluated in single-machine and multimachine power systems subjected to various transient disturbances. The new genetic-neuro-fuzzy control scheme exhibits a superior damping performance as well as a greater critical clearing time in comparison to the existing PI and RBFNN controller with updating of its parameters through the extended Kalman filter (EKF). Its simple architecture reduces the computational burden, thereby making it attractive for real-time implementation
Abstract: An integrated approach of radial basis function neural network (RBFNN) and Takagi-Sugeno (TS) fuzzy scheme with a genetic optimization of their parameters has been developed in this paper to design intelligent adaptive controllers for improving the transient stability performance of power systems. At the outset, this concept is applied to a simple device such as thyristor-controlled series capacitor (TCSC) connected in a single-machine infinite bus power system and is then extended to interline power-flow controller (IPFC) connected in a multimachine power system. The RBFNN uses single neuron architecture and its parameters are dynamically updated in an online fashion with TS-fuzzy scheme designed with only four rules and triangular membership function. The rules of the TS-fuzzy scheme are derived from the real- or reactive-power error and their derivatives either at the TCSC or IPFC buses depending on the device. Further, to implement this combined scheme only one coefficient in the TS-fuzzy rules needs to be optimized. The optimization of this coefficient as well as the coefficient for auxiliary signal generation is performed through genetic algorithm. The performance of the new controller is evaluated in single-machine and multimachine power systems subjected to various transient disturbances. The new genetic-neuro-fuzzy control scheme exhibits a superior damping performance as well as a greater critical clearing time in comparison to the existing PI and RBFNN controller with updating of its parameters through the extended Kalman filter (EKF). Its simple architecture reduces the computational burden, thereby making it attractive for real-time implementation
[42] Y. Y. He, "Chaotic simulated annealing with decaying chaotic noise," Ieee Transactions on Neural Networks, vol. 13, no. 6, pp. 1526-1531, Nov.2002.
Abstract: By adding chaotic noise to each neuron of the discrete-time continuous-output Hopfield neural network (HNN) and gradually reducing the noise, a chaotic neural network is proposed so that it is initially chaotic but eventually convergent, and, thus, has richer and more flexible dynamics compared to the HNN. The proposed network is applied to the traveling salesman problem (TSP) and that results are highly satisfactory. That is, the transient chaos enables the network to escape from local energy minima and to find global minima in 100% of the simulations for four-city and ten-city TSPs, as well as near-optimal solutions in most of runs for a 48-city TSP
Abstract: By adding chaotic noise to each neuron of the discrete-time continuous-output Hopfield neural network (HNN) and gradually reducing the noise, a chaotic neural network is proposed so that it is initially chaotic but eventually convergent, and, thus, has richer and more flexible dynamics compared to the HNN. The proposed network is applied to the traveling salesman problem (TSP) and that results are highly satisfactory. That is, the transient chaos enables the network to escape from local energy minima and to find global minima in 100% of the simulations for four-city and ten-city TSPs, as well as near-optimal solutions in most of runs for a 48-city TSP
[43] Q. Lu, W. C. Wang, C. Shen, S. W. Mei, M. Goto, and A. Yokoyama, "Intelligent optimal sieving method for FACTS device control in multi-machine systems," Electric Power Systems Research, vol. 62, no. 3, pp. 209-214, July2002.
Abstract: A multi-target oriented optimal control strategy for FACTS devices installed in multi-machine power systems is presented in this paper, which is named the intelligent optimal sieving control (IOSC) method. This new method divides the FACTS device output region into several parts and selects one typical value from each part, which is called output candidate. Then, an intelligent optimal sieve is constructed, which predicts the impacts of each output candidate on a power system and sieves out an optimal output from all of the candidates. The artificial neural network technologies and fuzzy methods are applied to build the intelligent sieve. Finally, the real control signal of FACTS devices is calculated according to the selected optimal output through inverse system method. Simulation has been done on a three-machine power system and the results show that the proposed IOSC controller can effectively attenuate system oscillations and enhance the power system transient stability.
Abstract: A multi-target oriented optimal control strategy for FACTS devices installed in multi-machine power systems is presented in this paper, which is named the intelligent optimal sieving control (IOSC) method. This new method divides the FACTS device output region into several parts and selects one typical value from each part, which is called output candidate. Then, an intelligent optimal sieve is constructed, which predicts the impacts of each output candidate on a power system and sieves out an optimal output from all of the candidates. The artificial neural network technologies and fuzzy methods are applied to build the intelligent sieve. Finally, the real control signal of FACTS devices is calculated according to the selected optimal output through inverse system method. Simulation has been done on a three-machine power system and the results show that the proposed IOSC controller can effectively attenuate system oscillations and enhance the power system transient stability.
[44] T. Senjyu, Y. Morishima, T. Arakaki, and K. Uezato, "Improvement of multimachine power system stability using adaptive PSS," Electric Power Components and Systems, vol. 30, no. 4, pp. 361-375, Apr.2002.
Abstract: The excitation controllers, such as automatic voltage regulator (AVR) and power system stabilizer (PSS) for improving electric power systems transient stability, have been installed on synchronous generators. A design procedure is shown for the controller parameter-tuning applying a genetic algorithm (GA). The PSS optimized by GA has a certain robustness; however, since the power system is nonlinear, drastic changes in the system caused by faults and circuit switching may cause control performance to become unsatisfactory. Then, a method using a nonlinear neural network can be used to tune the control Systems. This method of using neural networks has been reported in recent years. This paper presents an adaptive power system stabilizer (APSS) based on a recurrent neural network (RNN) to enhance the dynamic stability of a power system. The proposed APSS is applied in parallel with a conventional PSS (CPSS) to enhance the performance of power system stability. Both the APSS and CPSS is used for stabilizing signals. The APSS is constructed by a three-layered (8-9-1) RNN, of which inputs are DeltaP(e) and Deltaomega. The weights of APSS are adjusted online to maintain electrical output power deviation to zero. By applying the proposed APSS, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed APSS has been investigated in a three-machine power system
Abstract: The excitation controllers, such as automatic voltage regulator (AVR) and power system stabilizer (PSS) for improving electric power systems transient stability, have been installed on synchronous generators. A design procedure is shown for the controller parameter-tuning applying a genetic algorithm (GA). The PSS optimized by GA has a certain robustness; however, since the power system is nonlinear, drastic changes in the system caused by faults and circuit switching may cause control performance to become unsatisfactory. Then, a method using a nonlinear neural network can be used to tune the control Systems. This method of using neural networks has been reported in recent years. This paper presents an adaptive power system stabilizer (APSS) based on a recurrent neural network (RNN) to enhance the dynamic stability of a power system. The proposed APSS is applied in parallel with a conventional PSS (CPSS) to enhance the performance of power system stability. Both the APSS and CPSS is used for stabilizing signals. The APSS is constructed by a three-layered (8-9-1) RNN, of which inputs are DeltaP(e) and Deltaomega. The weights of APSS are adjusted online to maintain electrical output power deviation to zero. By applying the proposed APSS, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed APSS has been investigated in a three-machine power system
[45] A. H. M. A. Rahim and A. J. Al-Ramadhan, "Dynamic equivalent of external power system and its parameter estimation through artificial neural networks," International Journal of Electrical Power & Energy Systems, vol. 24, no. 2, pp. 113-120, Feb.2002.
Abstract: A multi-machine power network, external to a study system, has been replaced by one equivalent machine for dynamic studies. The backpropagation and radial-basis function neural networks have been employed to estimate unknown parameters of the dynamic equivalent. Transient stability indices like the peak overshoot, decay constant and frequency of oscillations of the study generator are used as input features to train the neural networks. While the back-propagation algorithm, generally, did not give very satisfactory estimates, the radial basis functions could be trained to predict the parameters of the equivalent with extreme precision. Estimating the dynamic equivalent from the transient stability indices is a novel approach.
Abstract: A multi-machine power network, external to a study system, has been replaced by one equivalent machine for dynamic studies. The backpropagation and radial-basis function neural networks have been employed to estimate unknown parameters of the dynamic equivalent. Transient stability indices like the peak overshoot, decay constant and frequency of oscillations of the study generator are used as input features to train the neural networks. While the back-propagation algorithm, generally, did not give very satisfactory estimates, the radial basis functions could be trained to predict the parameters of the equivalent with extreme precision. Estimating the dynamic equivalent from the transient stability indices is a novel approach.
[46] L. S. Moulin, A. P. A. da Silva, M. A. El-Sharkawi, and R. J. Marks, "Neural networks and support vector machines applied to power systems transient stability analysis," Engineering Intelligent Systems for Electrical Engineering and Communications, vol. 9, no. 4, pp. 205-211, Dec.2001.
Abstract: The Neural Network (NN) approach to the Transient Stability Analysis (TSA) has been presented as a potential tool for on-line applications, but the high dimensionality of the power systems turns it necessary to implement feature extraction techniques to make the application feasible in practice. This paper presents a new learning-based nonlinear classifier, the Support Vector Machines (SVMs) NNs, showing its suitability for power system TSA. It can be seen as a different approach to cope with the problem of high dimensionality due to its fast training capability, which can be combined with existing feature extraction techniques. SVMs' theoretical motivation is conceptually explained and they are applied to the IEEE 50 Generator system TSA problem. Aspects of model adequacy, training time and classification accuracy are discussed and compared to stability classifications obtained by Multi-Layer Perceptrons (MLPs)
Abstract: The Neural Network (NN) approach to the Transient Stability Analysis (TSA) has been presented as a potential tool for on-line applications, but the high dimensionality of the power systems turns it necessary to implement feature extraction techniques to make the application feasible in practice. This paper presents a new learning-based nonlinear classifier, the Support Vector Machines (SVMs) NNs, showing its suitability for power system TSA. It can be seen as a different approach to cope with the problem of high dimensionality due to its fast training capability, which can be combined with existing feature extraction techniques. SVMs' theoretical motivation is conceptually explained and they are applied to the IEEE 50 Generator system TSA problem. Aspects of model adequacy, training time and classification accuracy are discussed and compared to stability classifications obtained by Multi-Layer Perceptrons (MLPs)
[47] F. Allella and D. Lauria, "Fast optimal dispatch with global transient stability constraint," Iee Proceedings-Generation Transmission and Distribution, vol. 148, no. 5, pp. 471-476, Sept.2001.
Abstract: The modern electric power system operates with restricted stability margins. A new approach to on-line optimal dispatching, considering a global transient stability constraint, is proposed. The transient stability constraint is formulated in a probabilistic frame using the Lyapunov direct method. The approach leads to a constrained optimisation problem and the Chua neural network is used for problem solution. A numerical application to the New England test network is shown in the final part of the paper
Abstract: The modern electric power system operates with restricted stability margins. A new approach to on-line optimal dispatching, considering a global transient stability constraint, is proposed. The transient stability constraint is formulated in a probabilistic frame using the Lyapunov direct method. The approach leads to a constrained optimisation problem and the Chua neural network is used for problem solution. A numerical application to the New England test network is shown in the final part of the paper
[48] P. K. Dash, S. Mishra, and G. Panda, "A radial basis function neural network controller for UPFC," Ieee Transactions on Power Systems, vol. 15, no. 4, pp. 1293-1299, Nov.2000.
Abstract: This paper presents the design of radial basis function neural network controllers (RBFNN) for UPFC to improve the transient stability performance of a power system. The RBFNN uses either single neuron or multi-neuron architecture and the parameters are dynamically adjusted using an error surface derived from active or reactive power/voltage deviations at the UPFC injection bus. The performance of the new single neuron controller is evaluated using both single-machine infinite-bus and three-machine power systems subjected to various transient disturbances, In the case of three-machine 8-bus power system, the performance of the single neuron RBF controller is compared with BP (backpropagation) algorithm based multi-layered ANN controller Further it is seen that by using a multi-input multi-neuron RBF controller, instead of a single neuron one the critical clearing time and damping performance are improved. The new RBFNN controller for UPFC exhibits a superior damping performance in comparison to the existing PI controllers. Its simple architecture reduces the computational burden thereby making it attractive for real-time implementation
Abstract: This paper presents the design of radial basis function neural network controllers (RBFNN) for UPFC to improve the transient stability performance of a power system. The RBFNN uses either single neuron or multi-neuron architecture and the parameters are dynamically adjusted using an error surface derived from active or reactive power/voltage deviations at the UPFC injection bus. The performance of the new single neuron controller is evaluated using both single-machine infinite-bus and three-machine power systems subjected to various transient disturbances, In the case of three-machine 8-bus power system, the performance of the single neuron RBF controller is compared with BP (backpropagation) algorithm based multi-layered ANN controller Further it is seen that by using a multi-input multi-neuron RBF controller, instead of a single neuron one the critical clearing time and damping performance are improved. The new RBFNN controller for UPFC exhibits a superior damping performance in comparison to the existing PI controllers. Its simple architecture reduces the computational burden thereby making it attractive for real-time implementation
[49] H. S. Cho, J. K. Park, and G. W. Kim, "Power system transient stability analysis using Kohonen neural networks," Engineering Intelligent Systems for Electrical Engineering and Communications, vol. 7, no. 4, pp. 209-214, Dec.1999.
Abstract: This paper proposes two effective learning algorithms of Kohonen Neural Network (KNN) called Boundary Search Algorithm (BSA) and Iterative Condensed Nearest Neighbor (ICNN) rule. Compared with conventional learning algorithms of KNN, for example, Learning Vector Quantization (LVQ) method, the proposed learning algorithms place the codebook vectors near the decision boundaries. They are suitable especially for the problems where the decision boundary is clear such as power system stability evaluation. The effectiveness of the proposed algorithms is shown with the transient stability evaluation problem of a 4-generator, 6-bus sample power system
Abstract: This paper proposes two effective learning algorithms of Kohonen Neural Network (KNN) called Boundary Search Algorithm (BSA) and Iterative Condensed Nearest Neighbor (ICNN) rule. Compared with conventional learning algorithms of KNN, for example, Learning Vector Quantization (LVQ) method, the proposed learning algorithms place the codebook vectors near the decision boundaries. They are suitable especially for the problems where the decision boundary is clear such as power system stability evaluation. The effectiveness of the proposed algorithms is shown with the transient stability evaluation problem of a 4-generator, 6-bus sample power system
[50] M. G. Rabbani, J. B. X. Devotta, and S. Elangovan, "An ANN based controller for SMES units in power systems," Engineering Intelligent Systems for Electrical Engineering and Communications, vol. 7, no. 3, pp. 131-136, Sept.1999.
Abstract: A neural network based controller is designed for the Superconducting Magnetic Energy Storage Unit (SMES) to improve the transient stability of synchronous generators. The power modulation capability of the SMES is used to improve the dynamic performance of the system. The neural network is trained by learning linguistic rules. Normalized values of generator speed deviation and acceleration are used to train the network. The gain of the ANN controller is adapted on-line depending on the operating conditions. This allows the SMES unit to provide appropriate compensation required by the system following a disturbance. The control system is tested both for single and multi-machine systems. The simulation results show that the substantial improvement in stability is achieved when equipped with this type of control
Abstract: A neural network based controller is designed for the Superconducting Magnetic Energy Storage Unit (SMES) to improve the transient stability of synchronous generators. The power modulation capability of the SMES is used to improve the dynamic performance of the system. The neural network is trained by learning linguistic rules. Normalized values of generator speed deviation and acceleration are used to train the network. The gain of the ANN controller is adapted on-line depending on the operating conditions. This allows the SMES unit to provide appropriate compensation required by the system following a disturbance. The control system is tested both for single and multi-machine systems. The simulation results show that the substantial improvement in stability is achieved when equipped with this type of control
[51] A. I. Taalab, H. A. Darwish, and T. A. Kawady, "ANN-based novel fault detector for generator windings protection," Ieee Transactions on Power Delivery, vol. 14, no. 3, pp. 824-830, July1999.
Abstract: In this paper, an artificial neural network (ANN) based internal fault detector algorithm for generator protection is proposed. The detector uniquely responds to the winding earth and phase faults with remarkably high sensitivity. Discrimination of the fault type is provided via three trained ANNs having a six dimensional input vector. This input vector is obtained from the difference and average of the currents entering and leaving the generator windings. Training cases for the ANNs are generated via a simulation study of the generator internal faults using Electromagnetic Transient Program (EMTP). A genetic algorithm is employed to reduce training time. The proposed ANN algorithm is compared with a conventional differential algorithm. It is found to be superior regarding sensitivity and stability
Abstract: In this paper, an artificial neural network (ANN) based internal fault detector algorithm for generator protection is proposed. The detector uniquely responds to the winding earth and phase faults with remarkably high sensitivity. Discrimination of the fault type is provided via three trained ANNs having a six dimensional input vector. This input vector is obtained from the difference and average of the currents entering and leaving the generator windings. Training cases for the ANNs are generated via a simulation study of the generator internal faults using Electromagnetic Transient Program (EMTP). A genetic algorithm is employed to reduce training time. The proposed ANN algorithm is compared with a conventional differential algorithm. It is found to be superior regarding sensitivity and stability
[52] Y. Y. Hsu and T. S. Luor, "Damping of power system oscillations using adaptive thyristor-controlled series compensators tuned by artificial neural networks," Iee Proceedings-Generation Transmission and Distribution, vol. 146, no. 2, pp. 137-142, Mar.1999.
Abstract: A proportional-integral (PI) controller is designed for thyristor-controlled series compensators (TCSCs) to improve the damping for power system oscillations. To maintain a good damping characteristic over a wide range of operating conditions, the gains of the PI controller are adapted in real time, based on online measured transmission line loadings (real and reactive power flows). To speed up the online gain adaptation process, an artificial neural network which is capable of performing complicated computations in a parallel, distributed manner is designed. A major feature of the proposed adaptive PI controller is that only physically measurable variables (real and reactive power flows over the transmission line) are employed as inputs to the adaptive controller. To demonstrate the effectiveness of the proposed adaptive TCSC controller, computer simulations are performed on a power system under disturbance conditions. It is concluded from the simulation results that the proposed adaptive TCSC controller can yield satisfactory dynamic responses over a wide range of operating conditions. Low-frequency oscillations in the frequency range 0.3-2Hz have been effectively damped by the proposed compensators
Abstract: A proportional-integral (PI) controller is designed for thyristor-controlled series compensators (TCSCs) to improve the damping for power system oscillations. To maintain a good damping characteristic over a wide range of operating conditions, the gains of the PI controller are adapted in real time, based on online measured transmission line loadings (real and reactive power flows). To speed up the online gain adaptation process, an artificial neural network which is capable of performing complicated computations in a parallel, distributed manner is designed. A major feature of the proposed adaptive PI controller is that only physically measurable variables (real and reactive power flows over the transmission line) are employed as inputs to the adaptive controller. To demonstrate the effectiveness of the proposed adaptive TCSC controller, computer simulations are performed on a power system under disturbance conditions. It is concluded from the simulation results that the proposed adaptive TCSC controller can yield satisfactory dynamic responses over a wide range of operating conditions. Low-frequency oscillations in the frequency range 0.3-2Hz have been effectively damped by the proposed compensators
[53] M. Moechtar, A. S. Farag, L. Hu, and T. C. Cheng, "Combined genetic algorithms and neural-network approach for power-system transient stability evaluation," European Transactions on Electrical Power, vol. 9, no. 2, pp. 115-122, Mar.1999.
Abstract: As the electric power system grows in size and complexity with a large number of interconnections, the assessment of the transient stability of power systems became an extremely intricate and highly non-linear problem. Its solution needs either numerical methods involving bulk computations or specific dedicated methods to analyse dynamic non-linens systems. Either method mostly assesses, particularly in the post-fault condition, rite critical clearing time (CCT). This parameter constitutes very complex functional relationships between the pre-fault condition, type, and location of fault beside the clearance sequence. The available methods for evaluating such parameter had been previously reviewed. New approaches using the locally-tuned radial basis function (RBF) network, an artificial neural network (ANN) paradigm have been recently proposed The goal of this this paper is to develop methods that can combine both neural networks and genetic algorithms (GA) into a common framework, and apply them to prediction problems. in the paper the application of generic algorithms in selecting the input patterns for the RBF network is proposed. Description of this combined approach and the results of its application to two power systems, one for four-machine six-bus system and the other-for an existing system of North Sumatra, Indonesia, are also given in the paper The attainable results show that the performance of the RBF net work cart be maintained and improved in spite of less features in the input patterns
Abstract: As the electric power system grows in size and complexity with a large number of interconnections, the assessment of the transient stability of power systems became an extremely intricate and highly non-linear problem. Its solution needs either numerical methods involving bulk computations or specific dedicated methods to analyse dynamic non-linens systems. Either method mostly assesses, particularly in the post-fault condition, rite critical clearing time (CCT). This parameter constitutes very complex functional relationships between the pre-fault condition, type, and location of fault beside the clearance sequence. The available methods for evaluating such parameter had been previously reviewed. New approaches using the locally-tuned radial basis function (RBF) network, an artificial neural network (ANN) paradigm have been recently proposed The goal of this this paper is to develop methods that can combine both neural networks and genetic algorithms (GA) into a common framework, and apply them to prediction problems. in the paper the application of generic algorithms in selecting the input patterns for the RBF network is proposed. Description of this combined approach and the results of its application to two power systems, one for four-machine six-bus system and the other-for an existing system of North Sumatra, Indonesia, are also given in the paper The attainable results show that the performance of the RBF net work cart be maintained and improved in spite of less features in the input patterns
[54] C. W. Liu, M. C. Su, S. S. Tsay, and J. Y. Wang, "Application of a novel fuzzy neural network to real-time transient stability swings prediction based on synchronized phasor measurements," Ieee Transactions on Power Systems, vol. 14, no. 2, pp. 685-692, May1999.
Abstract: The ability to rapidly acquire synchronized phasor measurements from around the system opens up new possibilies for power system protection and control. In this paper we develop a novel class of fuzzy hyperrectangular composite neural networks which utilize synchronized phasor measurements to provide fast transient stability swings prediction for use with high-speed control. Primary features of the method include constructing a fuzzy neural network for all fault locations, using a short window of realistic-precision post-fault phasor measurements for the prediction, and testing robustness to variations in the operating point. From simulation tests on a sample power system, it reveals that the proposed tool can yield a highly successful prediction rate in real-time
Abstract: The ability to rapidly acquire synchronized phasor measurements from around the system opens up new possibilies for power system protection and control. In this paper we develop a novel class of fuzzy hyperrectangular composite neural networks which utilize synchronized phasor measurements to provide fast transient stability swings prediction for use with high-speed control. Primary features of the method include constructing a fuzzy neural network for all fault locations, using a short window of realistic-precision post-fault phasor measurements for the prediction, and testing robustness to variations in the operating point. From simulation tests on a sample power system, it reveals that the proposed tool can yield a highly successful prediction rate in real-time
[55] S. K. Tso, J. Liang, and X. X. Zhou, "Coordination of TCSC and SVC for improvement of power system performance with NN-based parameter adaptation," International Journal of Electrical Power & Energy Systems, vol. 21, no. 4, pp. 235-244, May1999.
Abstract: A nonlinear design technique, DFL (direct feedback linearizing), is used to deduce the control law for the TCSC (thyristor controlled series compensator) and SVC (static VAR compensator). The coordination between the two pieces of equipment is also designed in the paper with the SVC treated as the supplement of the TCSC. When operation of the TCSC is constrained by the inherent limitation of equipment, the adjustable SVC can supply the auxiliary support to improve the overall performance. In order to adapt to the changes of the operating mode and active power of generators, a neural network (NN) is applied to determine the control parameters of the equipment. Analysis and simulation of a case study have proved the effectiveness of the nonlinear control strategy.
Abstract: A nonlinear design technique, DFL (direct feedback linearizing), is used to deduce the control law for the TCSC (thyristor controlled series compensator) and SVC (static VAR compensator). The coordination between the two pieces of equipment is also designed in the paper with the SVC treated as the supplement of the TCSC. When operation of the TCSC is constrained by the inherent limitation of equipment, the adjustable SVC can supply the auxiliary support to improve the overall performance. In order to adapt to the changes of the operating mode and active power of generators, a neural network (NN) is applied to determine the control parameters of the equipment. Analysis and simulation of a case study have proved the effectiveness of the nonlinear control strategy.
[56] C. W. Liu, S. S. Tsay, Y. J. Wang, and M. C. Su, "Neuro-fuzzy approach to real-time transient stability prediction based on synchronized phasor measurements," Electric Power Systems Research, vol. 49, no. 2, pp. 123-127, Mar.1999.
Abstract: With new systems capable of making synchronized phasor measurements there are possibilities for real-time assessment of the stability of a transient swing in power systems. In the future, on-line control will be necessary as operating points are pushed closer toward the margin and fast reaction time becomes critical to the survival of the system. In this paper we develop a novel class of fuzzy hyperrectangular composite neural networks which utilize real-time phasor angle measurements to provide fast transient stability prediction for use with high-speed control. From simulation tests on a sample power system, it reveals that the proposed tool can yield a highly successful prediction rate in real-time.
Abstract: With new systems capable of making synchronized phasor measurements there are possibilities for real-time assessment of the stability of a transient swing in power systems. In the future, on-line control will be necessary as operating points are pushed closer toward the margin and fast reaction time becomes critical to the survival of the system. In this paper we develop a novel class of fuzzy hyperrectangular composite neural networks which utilize real-time phasor angle measurements to provide fast transient stability prediction for use with high-speed control. From simulation tests on a sample power system, it reveals that the proposed tool can yield a highly successful prediction rate in real-time.
[57] M. C. Su, C. W. Liu, and S. S. Tsay, "Neural-network-based fuzzy model and its application to transient stability prediction in power systems," Ieee Transactions on Systems Man and Cybernetics Part C-Applications and Reviews, vol. 29, no. 1, pp. 149-157, Feb.1999.
Abstract: This paper presents a general approach to deriving a new type of neural-network-based fuzzy model for a complex system from numerical and/or linguistic information. To efficiently identify the structure and the parameters of the new fuzzy model, we first partition the output space instead of the input space. As a result, the input space itself induces corresponding partitions within each of which inputs would have similar outputs. Then we use a set of hyperrectangles to fit the partitions of the input space. Consequently, the premise of an implication in the new type of fuzzy rule is represented by a hyperrectangle and the consequence is represented by a fuzzy singleton. A novel two-layer fuzzy hyperrectangular composite neural network (FHRCNN) can be shown to be computationally equivalent to such a special fuzzy model. The process of presenting input data to each hidden node in a FHRCNN is equivalent to Bring a fuzzy rule. An efficient learning algorithm was developed to adjust the weights of an FHRCNN. Finally, we apply FHRCNN's to provide real-time transient stability prediction for use with high-speed control in power systems. From simulation tests on the IEEE 39-bus system, it reveals that the proposed novel FHRCNN can yield a much better performance than that of conventional multilayer perceptrons (MLP's) in terms of computational burden and classification rate
Abstract: This paper presents a general approach to deriving a new type of neural-network-based fuzzy model for a complex system from numerical and/or linguistic information. To efficiently identify the structure and the parameters of the new fuzzy model, we first partition the output space instead of the input space. As a result, the input space itself induces corresponding partitions within each of which inputs would have similar outputs. Then we use a set of hyperrectangles to fit the partitions of the input space. Consequently, the premise of an implication in the new type of fuzzy rule is represented by a hyperrectangle and the consequence is represented by a fuzzy singleton. A novel two-layer fuzzy hyperrectangular composite neural network (FHRCNN) can be shown to be computationally equivalent to such a special fuzzy model. The process of presenting input data to each hidden node in a FHRCNN is equivalent to Bring a fuzzy rule. An efficient learning algorithm was developed to adjust the weights of an FHRCNN. Finally, we apply FHRCNN's to provide real-time transient stability prediction for use with high-speed control in power systems. From simulation tests on the IEEE 39-bus system, it reveals that the proposed novel FHRCNN can yield a much better performance than that of conventional multilayer perceptrons (MLP's) in terms of computational burden and classification rate
[58] W. A. Farag, V. H. Quintana, and G. Lambert-Torres, "An optimized fuzzy controller for a synchronous generator in a multi-machine environment," Fuzzy Sets and Systems, vol. 102, no. 1, pp. 71-84, Feb.1999.
Abstract: In this paper, an optimized neuro-fuzzy power-system stabilizer (NF PSS) is proposed to improve the transient and dynamic stability of synchronous machines. The NF PSS employs a five-layer fuzzy-neural network (FNN). The learning scheme of this FNN is composed of three phases. The first phase uses a clustering algorithm for coarse identification of the initial membership functions of the fuzzy controller (FC). The second phase extracts the linguistic-fuzzy rules from the available training data. In the third phase, a multi-resolutional dynamic genetic algorithm (MRD-GA) is used to fine-tune and optimize the membership functions of the FC. Extensive simulation studies have been carried out to show the performance of the NF PSS and to compare it with a Conventional PSS (CPSS) in a multi-machine power-system environment.
Abstract: In this paper, an optimized neuro-fuzzy power-system stabilizer (NF PSS) is proposed to improve the transient and dynamic stability of synchronous machines. The NF PSS employs a five-layer fuzzy-neural network (FNN). The learning scheme of this FNN is composed of three phases. The first phase uses a clustering algorithm for coarse identification of the initial membership functions of the fuzzy controller (FC). The second phase extracts the linguistic-fuzzy rules from the available training data. In the third phase, a multi-resolutional dynamic genetic algorithm (MRD-GA) is used to fine-tune and optimize the membership functions of the FC. Extensive simulation studies have been carried out to show the performance of the NF PSS and to compare it with a Conventional PSS (CPSS) in a multi-machine power-system environment.
[59] S. K. Tso, X. P. Gu, Q. Y. Zeng, and K. L. Lo, "Deriving a transient stability index by neural networks for power-system security assessment," Engineering Applications of Artificial Intelligence, vol. 11, no. 6, pp. 771-779, Dec.1998.
Abstract: This paper proposes an approach for establishing a transient stability classifier and derives a continuous transient stability index, using a three-layer feed-forward artificial neural network (ANN), for on-line security assessment in large power systems. With the derived stability index, a never classification scheme creating an 'indeterminate' class, is introduced to minimize misclassifications and to improve the reliability of the classification results. Several post-fault abstract attributes about the system generators' acceleration rates and kinetic energies provide the basis for the stability classification. In order to derive the transient stability index, a semi-supervised backpropagation (BP) learning algorithm, making use of a specially defined error function, is developed. The proposed approach can not only distinguish whether a power system is stable or unstable, on the basis of the specific post-fault attributes, but can also provide a relative stability quantifier. Furthermore, as the number of the selected abstract attributes is independent of the system size, the methodology of the proposed approach can realistically be applied to large power systems. The 10-unit 39-bus New England power system is employed to demonstrate the proposed approach. The numerical results show that the ANN-based classifier can assess the transient stability reasonably well.
Abstract: This paper proposes an approach for establishing a transient stability classifier and derives a continuous transient stability index, using a three-layer feed-forward artificial neural network (ANN), for on-line security assessment in large power systems. With the derived stability index, a never classification scheme creating an 'indeterminate' class, is introduced to minimize misclassifications and to improve the reliability of the classification results. Several post-fault abstract attributes about the system generators' acceleration rates and kinetic energies provide the basis for the stability classification. In order to derive the transient stability index, a semi-supervised backpropagation (BP) learning algorithm, making use of a specially defined error function, is developed. The proposed approach can not only distinguish whether a power system is stable or unstable, on the basis of the specific post-fault attributes, but can also provide a relative stability quantifier. Furthermore, as the number of the selected abstract attributes is independent of the system size, the methodology of the proposed approach can realistically be applied to large power systems. The 10-unit 39-bus New England power system is employed to demonstrate the proposed approach. The numerical results show that the ANN-based classifier can assess the transient stability reasonably well.
[60] W. A. Farag, V. H. Quintana, and G. Torres, "Applications of artificial intelligence techniques in synchronous machine control: a review," Engineering Intelligent Systems for Electrical Engineering and Communications, vol. 6, no. 2, pp. 65-73, June1998.
Abstract: To enhance power systems stability, extensive research has been conducted in the area of synchronous machines control, and several techniques and algorithms have been developed and implemented in real applications. One of the latest and most sophisticated techniques is the Artificial Intelligence (AI) based control. Increased interest has been focused in the use of these algorithms in control systems; different approaches have been proposed for their application. The results presented on several research papers show the advantages of such algorithms over the conventional control algorithms. In this paper, the problem of synchronous machines control is considered, and an overview of several artificial intelligence approaches as applied to the control of synchronous generators is presented. A critical and evaluating discussion on each AI approach is also included
Abstract: To enhance power systems stability, extensive research has been conducted in the area of synchronous machines control, and several techniques and algorithms have been developed and implemented in real applications. One of the latest and most sophisticated techniques is the Artificial Intelligence (AI) based control. Increased interest has been focused in the use of these algorithms in control systems; different approaches have been proposed for their application. The results presented on several research papers show the advantages of such algorithms over the conventional control algorithms. In this paper, the problem of synchronous machines control is considered, and an overview of several artificial intelligence approaches as applied to the control of synchronous generators is presented. A critical and evaluating discussion on each AI approach is also included
[61] N. Amjady and M. Ehsan, "Transient stability assessment of power systems by a new estimating neural network," Canadian Journal of Electrical and Computer Engineering-Revue Canadienne de Genie Electrique et Informatique, vol. 22, no. 3, pp. 131-137, July1997.
Abstract: The problem of transient stability assessment and its difficulties are explained. An expert system using a neural network that is appropriate for determination of transient stability of power systems is discussed in the paper. This neural network is applied to determine the critical clearing times in a disturbed power system. Applications of this method and its advantages and disadvantages are discussed
Abstract: The problem of transient stability assessment and its difficulties are explained. An expert system using a neural network that is appropriate for determination of transient stability of power systems is discussed in the paper. This neural network is applied to determine the critical clearing times in a disturbed power system. Applications of this method and its advantages and disadvantages are discussed
[62] T. Hiyama, M. Tokieda, W. Hubbi, and H. Andou, "Artificial neural network based dynamic load modeling," Ieee Transactions on Power Systems, vol. 12, no. 4, pp. 1576-1583, Nov.1997.
Abstract: The aim of this research is to investigate the use of Artificial Neural Networks (ANN) with feedback loops For modeling power system dynamic loads using field data. In addition to the power demand before the transient, only the phase voltages will be assumed available at the recall stage. It is found that the load dynamics can be identified using the ANN developed for the season and the location of the load being emulated. The frequency response of the tested load is also obtained using the achieved ANN model
Abstract: The aim of this research is to investigate the use of Artificial Neural Networks (ANN) with feedback loops For modeling power system dynamic loads using field data. In addition to the power demand before the transient, only the phase voltages will be assumed available at the recall stage. It is found that the load dynamics can be identified using the ANN developed for the season and the location of the load being emulated. The frequency response of the tested load is also obtained using the achieved ANN model
[63] S. Chauhan and M. P. Dave, "Input-features based comparative study of intelligent transient stability assessment," Electric Machines and Power Systems, vol. 25, no. 6, pp. 593-605, July1997.
Abstract: With the growing stress on today's power system, it is operated much closer to its stability limit. Under such circumstances it is highly desirable that one must be able to assess the security and stability of the electric power system when exposed to disturbances/faults. In the post-fault transient analysis of interconnected systems, the transient energy margin which is a complex function of prefault system conditions, structure of fault (type and location) and network topology at the specified fault clearing time gives a quantitative idea about the stability of the system. High adaptation capabilities of artificial neural networks make them capable of synthesizing the complex mapping that transform the input features in to a single-valued space of energy margin. Appropriate input feature selection has a direct bearing on the consistency and accuracy of mapping. This issue has been addressed in the present paper by comparing the prediction results based on approaches (Sobajic and Pao, 1989), (Sobajic and Pao 1992) (Jeyasurya, 1993) in the time domain, energy domain and its corresponding time domain calibration. Subsequent to the above comparison, the much haunting question of whether to train the network in the energy or time domain has been answered satisfactorily. It has been observed that fault clearing time is a key parameter that anticipates the success of possible calibration of energy margin results into the time domain. Test cases for prediction have been collected from many different operating conditions in power systems. Multilayer perceptron model with ADAPTIVE LEARNING ALGORITHM is used to carry out the present studies
Abstract: With the growing stress on today's power system, it is operated much closer to its stability limit. Under such circumstances it is highly desirable that one must be able to assess the security and stability of the electric power system when exposed to disturbances/faults. In the post-fault transient analysis of interconnected systems, the transient energy margin which is a complex function of prefault system conditions, structure of fault (type and location) and network topology at the specified fault clearing time gives a quantitative idea about the stability of the system. High adaptation capabilities of artificial neural networks make them capable of synthesizing the complex mapping that transform the input features in to a single-valued space of energy margin. Appropriate input feature selection has a direct bearing on the consistency and accuracy of mapping. This issue has been addressed in the present paper by comparing the prediction results based on approaches (Sobajic and Pao, 1989), (Sobajic and Pao 1992) (Jeyasurya, 1993) in the time domain, energy domain and its corresponding time domain calibration. Subsequent to the above comparison, the much haunting question of whether to train the network in the energy or time domain has been answered satisfactorily. It has been observed that fault clearing time is a key parameter that anticipates the success of possible calibration of energy margin results into the time domain. Test cases for prediction have been collected from many different operating conditions in power systems. Multilayer perceptron model with ADAPTIVE LEARNING ALGORITHM is used to carry out the present studies
[64] Y. Mansour, E. Vaahedi, and M. A. ElSharkawi, "Dynamic security contingency screening and ranking using neural networks," Ieee Transactions on Neural Networks, vol. 8, no. 4, pp. 942-950, May1997.
Abstract: This paper summarizes B.C. Hydro's experience in applying neural networks to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of B.C. Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for B.C. Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (second kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security; However a number of corrective measures improved the results significantly. These corrective measures included: 1) the effectiveness of output; 2) the number of outputs; 3) the type of features (static versus dynamic); 4) the number of features; 5) system partitioning; and 6) the ratio of training samples to features. The final results obtained using the large scare systems of B.C. Hydro and Hydro Quebec demonstrates a goad potential for neural network in dynamic security assessment contingency screening and ranking
Abstract: This paper summarizes B.C. Hydro's experience in applying neural networks to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of B.C. Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for B.C. Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (second kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security; However a number of corrective measures improved the results significantly. These corrective measures included: 1) the effectiveness of output; 2) the number of outputs; 3) the type of features (static versus dynamic); 4) the number of features; 5) system partitioning; and 6) the ratio of training samples to features. The final results obtained using the large scare systems of B.C. Hydro and Hydro Quebec demonstrates a goad potential for neural network in dynamic security assessment contingency screening and ranking
[65] Y. Mansour, E. Vaahedi, M. A. ElSharkawi, A. Y. Chang, B. R. Corns, and J. Tamby, "Large scale dynamic security screening and ranking using neural networks," Ieee Transactions on Power Systems , vol. 12, no. 2, pp. 954-960, May1997.
Abstract: This paper reports on the findings of a recently completed Canadian Electric Association (CEA) funded project [1] exploring the application of neural network to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of B.C. Hydro and Hydro Quebec, in total 1691 derailed transient stability simulation were conducted, 1158 for B.C. Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the Energy Margin Calculation Module (Second Kick) [4] to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included : a) the effectiveness of output, b) the number of outputs, c) the type of features (static versus dynamic), d) the number of features, e) system partitioning and f) the ratio of training samples to features. The final results obtained using the large scale systems of B.C. Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking
Abstract: This paper reports on the findings of a recently completed Canadian Electric Association (CEA) funded project [1] exploring the application of neural network to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of B.C. Hydro and Hydro Quebec, in total 1691 derailed transient stability simulation were conducted, 1158 for B.C. Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the Energy Margin Calculation Module (Second Kick) [4] to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included : a) the effectiveness of output, b) the number of outputs, c) the type of features (static versus dynamic), d) the number of features, e) system partitioning and f) the ratio of training samples to features. The final results obtained using the large scale systems of B.C. Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking
[66] K. Pakdaman, C. P. Malta, C. GrottaRagazzo, O. Arino, and J. F. Vibert, "Transient oscillations in continuous-time excitatory ring neural networks with delay," Physical Review e, vol. 55, no. 3, pp. 3234-3248, Mar.1997.
Abstract: A ring neural network is a closed chain in which each unit is connected unidirectionally to the next one. Numerical investigations indicate that continuous-time excitatory ring networks composed of graded-response units can generate oscillations when interunit transmission is delayed. These oscillations appear for a wide range of initial conditions. The mechanisms underlying the generation of such patterns of activity are studied. The analysis of the asymptotic behavior of the system shows that (i) trajectories of most initial conditions tend to stable equilibria, (ii) undamped oscillations are unstable, and can only exist in a narrow region forming the boundary between the basins of attraction of the stable equilibria. Therefore the analysis of the asymptotic behavior of the system is not sufficient to explain the oscillations observed numerically when interunit transmission is delayed. This analysis corroborates the hypothesis that the oscillations are transient. In fact, it is shown that the transient behavior of the system with delay follows that of the corresponding discrete-time excitatory ring network. The latter displays infinitely many nonconstant periodic oscillations that transiently attract the trajectories of the network with delay, leading to long-lasting transient oscillations. The duration of these oscillations increases exponentially with the inverse of the characteristic charge-discharge time of the neurons, indicating that they can outlast observation windows in numerical investigations. Therefore, for practical applications, these transients cannot be distinguished from stationary oscillations. It is argued that understanding the transient behavior of neural network models is an important. complement to the analysis of their asymptotic behavior, since both living nervous systems and artificial neural networks may operate in changing environments where long-lasting transients are functionally indistinguishable from asymptotic regimes
Abstract: A ring neural network is a closed chain in which each unit is connected unidirectionally to the next one. Numerical investigations indicate that continuous-time excitatory ring networks composed of graded-response units can generate oscillations when interunit transmission is delayed. These oscillations appear for a wide range of initial conditions. The mechanisms underlying the generation of such patterns of activity are studied. The analysis of the asymptotic behavior of the system shows that (i) trajectories of most initial conditions tend to stable equilibria, (ii) undamped oscillations are unstable, and can only exist in a narrow region forming the boundary between the basins of attraction of the stable equilibria. Therefore the analysis of the asymptotic behavior of the system is not sufficient to explain the oscillations observed numerically when interunit transmission is delayed. This analysis corroborates the hypothesis that the oscillations are transient. In fact, it is shown that the transient behavior of the system with delay follows that of the corresponding discrete-time excitatory ring network. The latter displays infinitely many nonconstant periodic oscillations that transiently attract the trajectories of the network with delay, leading to long-lasting transient oscillations. The duration of these oscillations increases exponentially with the inverse of the characteristic charge-discharge time of the neurons, indicating that they can outlast observation windows in numerical investigations. Therefore, for practical applications, these transients cannot be distinguished from stationary oscillations. It is argued that understanding the transient behavior of neural network models is an important. complement to the analysis of their asymptotic behavior, since both living nervous systems and artificial neural networks may operate in changing environments where long-lasting transients are functionally indistinguishable from asymptotic regimes
[67] T. Kobayashi, Y. Morioka, and A. Yokoyama, "Damping enhancement of multimachine power system using adaptive generator control system with neural networks," Electrical Engineering in Japan, vol. 117, no. 4, pp. 46-60, Oct.1996.
Abstract: The authors proposed a nonlinear adaptive generator control system with neutral networks for improving damping of power systems, and showed its effectiveness in a one-machine infinite bus test power system in a previous paper. The proposed neurocontrol system adaptively generates appropriate supplementary control signals to the conventional controllers such as the automatic voltage regulator and speed governor so as to enhance transient stability and damping of the power system. In this paper, the applicability of the proposed neurocontrol system to multimachine power systems is discussed. Digital time simulations are carried out for a 4-machine test power system, where one or several synchronous generators is equipped with the neurocontrol system. As. a result, also in the multimachine power system, the proposed adaptive neurocontrol systems improve the system damping effectively and they work adaptively against the wide changes of the operating conditions and the network configuration
Abstract: The authors proposed a nonlinear adaptive generator control system with neutral networks for improving damping of power systems, and showed its effectiveness in a one-machine infinite bus test power system in a previous paper. The proposed neurocontrol system adaptively generates appropriate supplementary control signals to the conventional controllers such as the automatic voltage regulator and speed governor so as to enhance transient stability and damping of the power system. In this paper, the applicability of the proposed neurocontrol system to multimachine power systems is discussed. Digital time simulations are carried out for a 4-machine test power system, where one or several synchronous generators is equipped with the neurocontrol system. As. a result, also in the multimachine power system, the proposed adaptive neurocontrol systems improve the system damping effectively and they work adaptively against the wide changes of the operating conditions and the network configuration
[68] A. R. Edwards, K. W. Chan, R. W. Dunn, and A. R. Daniels, "Transient stability screening using artificial neural networks within a dynamic security assessment system," Iee Proceedings-Generation Transmission and Distribution, vol. 143, no. 2, pp. 129-134, Mar.1996.
Abstract: Accurate assessment of transient and dynamic stability provided by an online dynamic security assessor allows the power system to be operated closer to its stability limits with considerable economic benefit through the running of less out-of-merit generation. As part of such assessors, contingency screens are used to filter out those contingencies which pose no stability problems. Those contingencies which pass through these filters are evaluated in detail to determine their effects on the system stability. The paper describes an approach where an artificial neural network is successfully used to provide a fast transient stability screen within a dynamic security assessment system. Results are presented for a number of test networks based on a reduced model of the UK National Grid System
Abstract: Accurate assessment of transient and dynamic stability provided by an online dynamic security assessor allows the power system to be operated closer to its stability limits with considerable economic benefit through the running of less out-of-merit generation. As part of such assessors, contingency screens are used to filter out those contingencies which pose no stability problems. Those contingencies which pass through these filters are evaluated in detail to determine their effects on the system stability. The paper describes an approach where an artificial neural network is successfully used to provide a fast transient stability screen within a dynamic security assessment system. Results are presented for a number of test networks based on a reduced model of the UK National Grid System
[69] T. Maeda, K. Takigawa, Y. Minato, and A. Yokoyama, "Assessment of transient voltage stability based on critical operating time of emergency control using neural networks," Electrical Engineering in Japan, vol. 115, no. 8, pp. 33-43, Dec.1995.
Abstract: Since unstable phenomena that load bus voltages collapse rapidly after a large disturbance occurred in a bulk power system, it is becoming necessary to develop a fast and precise evaluation method of what is called transient voltage stability. Although many indices have so far been proposed for static voltage stability assessment, there are few evaluation methods, digital simulation analysis for example, for the transient voltage stability assessment that deals with the dynamic characteristics of generators, loads, etc. This paper presents the transient voltage stability evaluation system that consists of two artificial neural networks (NNs). The first NN judges whether the system is stable or not under a given operating condition, load composition and fault location from the viewpoint of the transient voltage stability. If it is judged to be unstable, the second NN estimates critical operating time of emergency control action as a severity index of the transient voltage instability. Here, closing of a bus tie that is switched off in the normal state is adopted as the emergency control for voltage stabilization. Numerical examples for a 26-bus model system are shown in order to check the effectiveness of the proposed evaluation system
Abstract: Since unstable phenomena that load bus voltages collapse rapidly after a large disturbance occurred in a bulk power system, it is becoming necessary to develop a fast and precise evaluation method of what is called transient voltage stability. Although many indices have so far been proposed for static voltage stability assessment, there are few evaluation methods, digital simulation analysis for example, for the transient voltage stability assessment that deals with the dynamic characteristics of generators, loads, etc. This paper presents the transient voltage stability evaluation system that consists of two artificial neural networks (NNs). The first NN judges whether the system is stable or not under a given operating condition, load composition and fault location from the viewpoint of the transient voltage stability. If it is judged to be unstable, the second NN estimates critical operating time of emergency control action as a severity index of the transient voltage instability. Here, closing of a bus tie that is switched off in the normal state is adopted as the emergency control for voltage stabilization. Numerical examples for a 26-bus model system are shown in order to check the effectiveness of the proposed evaluation system
[70] H. Tsai, A. Keyhani, J. A. Demco, and D. A. Selin, "Development of a neural network based saturation model for synchronous generator analysis," Ieee Transactions on Energy Conversion, vol. 10, no. 4, pp. 617-624, Dec.1995.
Abstract: This paper presents a new approach to model the synchronous generator saturation based on a feed-forward artificial neural network (ANN) model. The machine loading conditions, excitation levels and rotor positions are all included in the modeling process. The nonlinear saturation characteristics of a three-phase salient-pole synchronous machine rated at 5 kVA and 240 V is studied using the ANN model. An appropriate selection of input/output pattern for the ANN model training based on error back-propagation scheme [5] is developed using the on-line small-disturbance responses and the well-known maximum-likelihood estimation algorithm]. The developed ANN model is implemented in the generator dynamic transient stability study requiring only small computational alteration in saturation model representation
Abstract: This paper presents a new approach to model the synchronous generator saturation based on a feed-forward artificial neural network (ANN) model. The machine loading conditions, excitation levels and rotor positions are all included in the modeling process. The nonlinear saturation characteristics of a three-phase salient-pole synchronous machine rated at 5 kVA and 240 V is studied using the ANN model. An appropriate selection of input/output pattern for the ANN model training based on error back-propagation scheme [5] is developed using the on-line small-disturbance responses and the well-known maximum-likelihood estimation algorithm]. The developed ANN model is implemented in the generator dynamic transient stability study requiring only small computational alteration in saturation model representation
[71] T. Kobayashi, A. Yokoyama, and Y. Morioka, "Synchronous Generator Control Using Neural-Network-Based Nonlinear Adaptive Regulator," Electrical Engineering in Japan, vol. 115, no. 5, pp. 38-51, Aug.1995.
Abstract: Control equipment of synchronous generators such as automatic voltage regulators, speed governors and power system stabilizers have been developed to maintain stability and to improve damping of power systems. When an operating condition changes greatly, however, such controllers may become less effective because of nonlinearity of the power system. In this paper, a nonlinear adaptive generator control system using neural networks is proposed. The proposed neurocontrol system consists of two neural networks which work as an identifier and a controller, respectively, and generates supplementary control signals to the conventional controllers. An essential feature of the proposed system is that the internal connection weights of both neural networks are adjusted adaptively so as to generate appropriate control signals for transient stability and damping enhancement in response to changes of the operating conditions and the network configuration. To investigate the control performance of the proposed neurocontrol system, digital time simulations are carried out for a one-machine infinite bus model system. As a result, it is clarified that the proposed adaptive neurocontrol system effectively improves the system damping and shows adaptability against the wide changes of the operating conditions
Abstract: Control equipment of synchronous generators such as automatic voltage regulators, speed governors and power system stabilizers have been developed to maintain stability and to improve damping of power systems. When an operating condition changes greatly, however, such controllers may become less effective because of nonlinearity of the power system. In this paper, a nonlinear adaptive generator control system using neural networks is proposed. The proposed neurocontrol system consists of two neural networks which work as an identifier and a controller, respectively, and generates supplementary control signals to the conventional controllers. An essential feature of the proposed system is that the internal connection weights of both neural networks are adjusted adaptively so as to generate appropriate control signals for transient stability and damping enhancement in response to changes of the operating conditions and the network configuration. To investigate the control performance of the proposed neurocontrol system, digital time simulations are carried out for a one-machine infinite bus model system. As a result, it is clarified that the proposed adaptive neurocontrol system effectively improves the system damping and shows adaptability against the wide changes of the operating conditions
[72] H. C. Chang and M. H. Wang, "Neural-Network-Based Self-Organizing Fuzzy Controller for Transient Stability of Multimachine Power-Systems," Ieee Transactions on Energy Conversion, vol. 10, no. 2, pp. 339-347, June1995.
Abstract: An efficient self-organizing neural fuzzy controller (SONFC) is designed to improve the transient stability of multimachine power systems. First, an artificial neural network (ANN)-based model is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the ANN model, With the excellent learning capability inherent in the ANN, the traditional heuristic fuzzy control rules and input/output fuzzy membership functions can be optimally tuned from training examples by the backpropagation learning algorithm. Considerable rule-matching times of the inference engine in the traditional fuzzy system can be saved. To illustrate the performance and usefulness of the SONFC, comparative studies with a bang-bang controller are performed on the 34-generator Taipower system with rather encouraging results
Abstract: An efficient self-organizing neural fuzzy controller (SONFC) is designed to improve the transient stability of multimachine power systems. First, an artificial neural network (ANN)-based model is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the ANN model, With the excellent learning capability inherent in the ANN, the traditional heuristic fuzzy control rules and input/output fuzzy membership functions can be optimally tuned from training examples by the backpropagation learning algorithm. Considerable rule-matching times of the inference engine in the traditional fuzzy system can be saved. To illustrate the performance and usefulness of the SONFC, comparative studies with a bang-bang controller are performed on the 34-generator Taipower system with rather encouraging results
[73] V. Miranda, J. N. Fidalgo, J. A. P. Lopes, and L. B. Almeida, "Real-Time Preventive Actions for Transient Stability Enhancement with A Hybrid Neural-Network - Optimization Approach," Ieee Transactions on Power Systems, vol. 10, no. 2, pp. 1029-1035, May1995.
Abstract: This paper reports a new approach in defining preventive control measures to assure transient stability relatively to one or several contingencies that may occur separately in a power system. Generation dispatch is driven not only by economic functions but also with the derivatives of the transient energy margin value; these derivatives are obtained directly from a trained Artificial Neural Network (ANN), using ri:al time monitorable system values. Results obtained from computer simulations, for several contingencies in the CIGRE test system, confirm the validity of the developed approach
Abstract: This paper reports a new approach in defining preventive control measures to assure transient stability relatively to one or several contingencies that may occur separately in a power system. Generation dispatch is driven not only by economic functions but also with the derivatives of the transient energy margin value; these derivatives are obtained directly from a trained Artificial Neural Network (ANN), using ri:al time monitorable system values. Results obtained from computer simulations, for several contingencies in the CIGRE test system, confirm the validity of the developed approach
[74] P. K. Dash and A. C. Liew, "Anticipatory Fuzzy Control of Power-Systems," Iee Proceedings-Generation Transmission and Distribution, vol. 142, no. 2, pp. 211-218, Mar.1995.
Abstract: The paper presents an anticipatory fuzzy control to improve the stability of electric power systems. This differs from the traditional fuzzy control in that, once the fuzzy-control rules have been used to generate a control value, a predictive routine built into the controller is called for anticipating its effect on the system output and hence updating the rule base or input-output membership functions in the event of unsatisfactory performance. The effectiveness of the anticipatory and traditional PI fuzzy controllers is demonstrated by simulation studies on a single-machine infinite-bus and multimachine power system subjected to a variety of transient disturbances for different operating conditions. The anticipatory fuzzy control, however, requires a neural-network prediction routine using modified-Kalman-filter-based fast-learning algorithm
Abstract: The paper presents an anticipatory fuzzy control to improve the stability of electric power systems. This differs from the traditional fuzzy control in that, once the fuzzy-control rules have been used to generate a control value, a predictive routine built into the controller is called for anticipating its effect on the system output and hence updating the rule base or input-output membership functions in the event of unsatisfactory performance. The effectiveness of the anticipatory and traditional PI fuzzy controllers is demonstrated by simulation studies on a single-machine infinite-bus and multimachine power system subjected to a variety of transient disturbances for different operating conditions. The anticipatory fuzzy control, however, requires a neural-network prediction routine using modified-Kalman-filter-based fast-learning algorithm
[75] A. M. Sharaf and T. T. Lie, "Ann Based Pattern-Classification of Synchronous Generator Stability and Loss of Excitation," Ieee Transactions on Energy Conversion, vol. 9, no. 4, pp. 753-759, Dec.1994.
Abstract: The paper presents a novel Artificial Intelligence (AI) based Neural Network (ANN) pattern classification and on-line detection scheme for a single machine infinite bus system. The proposed on-line relay and dynamic pattern classifier utilizes specific frequency spectra of the hyperplane discriminant vector of machine rotor angle, speed, accelerating power, instantaneous power, voltage, and current using either a perception single layer detection scheme or a two layer feed forward ANN for on-line classification and detection of fault condition causing first swing transient stability or loss of excitation. Other relay binary outputs include fault type and allowable clearing time identification. The detection accuracy is improved by utilizing the cross spectra of discriminant vector input variables correlations. The proposed pattern classification technique can be extended to interconnected multi-machine systems by using relative rotor angles, frequency deviations, tie-line powers, and their cross spectra variables
Abstract: The paper presents a novel Artificial Intelligence (AI) based Neural Network (ANN) pattern classification and on-line detection scheme for a single machine infinite bus system. The proposed on-line relay and dynamic pattern classifier utilizes specific frequency spectra of the hyperplane discriminant vector of machine rotor angle, speed, accelerating power, instantaneous power, voltage, and current using either a perception single layer detection scheme or a two layer feed forward ANN for on-line classification and detection of fault condition causing first swing transient stability or loss of excitation. Other relay binary outputs include fault type and allowable clearing time identification. The detection accuracy is improved by utilizing the cross spectra of discriminant vector input variables correlations. The proposed pattern classification technique can be extended to interconnected multi-machine systems by using relative rotor angles, frequency deviations, tie-line powers, and their cross spectra variables
[76] D. R. Marpaka, M. Bodruzzaman, S. S. Devgan, S. M. Aghili, and S. Kari, "Neural-Network-Based Transient Stability Assessment of Electric-Power Systems," Electric Power Systems Research, vol. 30, no. 3, pp. 251-256, Sept.1994.
Abstract: In this paper a systematic procedure to design an intelligent neurocontroller to assess the dynamic security of interconnected power systems is presented. This approach focuses on the integration of modern control theory together with the adaptive networks to determine critical clearing time for power systems
Abstract: In this paper a systematic procedure to design an intelligent neurocontroller to assess the dynamic security of interconnected power systems is presented. This approach focuses on the integration of modern control theory together with the adaptive networks to determine critical clearing time for power systems
[77] A. M. Sharaf and T. T. Lie, "Artificial Neural-Network Pattern-Classification of Transient Stability and Loss of Excitation for Synchronous Generators," Electric Power Systems Research, vol. 30, no. 1, pp. 9-16, June1994.
Abstract: A novel artificial intelligence based neural network (ANN) global online fault detection, pattern classification, and relaying detection scheme for synchronous generators in interconnected electric utility networks is presented. The input discriminant vector comprises the fast Fourier transform (FFT) dominant frequency spectra of eighteen input variables forming the discriminant diagnostic hyperplane. The online ANN based relaying scheme classifies fault existence, fault type as either transient stability or loss of excitation, the allowable critical clearing time, and loss of excitation type as either open-circuit or short-circuit field conditions. The proposed FFT dominant-frequency based hyperplane diagnostic technique can be easily extended to multimachine electric interconnected AC systems
Abstract: A novel artificial intelligence based neural network (ANN) global online fault detection, pattern classification, and relaying detection scheme for synchronous generators in interconnected electric utility networks is presented. The input discriminant vector comprises the fast Fourier transform (FFT) dominant frequency spectra of eighteen input variables forming the discriminant diagnostic hyperplane. The online ANN based relaying scheme classifies fault existence, fault type as either transient stability or loss of excitation, the allowable critical clearing time, and loss of excitation type as either open-circuit or short-circuit field conditions. The proposed FFT dominant-frequency based hyperplane diagnostic technique can be easily extended to multimachine electric interconnected AC systems
[78] C. S. Chang, D. Srinivasan, and A. C. Liew, "A Hybrid Model for Transient Stability Evaluation of Interconnected Longitudinal Power-Systems Using Neural-Network Pattern-Recognition Approach," Ieee Transactions on Power Systems, vol. 9, no. 1, pp. 85-92, Feb.1994.
Abstract: A methodology for evaluation of transient stability of medium size interconnected longitudinal power systems has been developed using a hybrid neural network/pattern recognition approach. Assessment of transient stability is done using a fast pattern recognition algorithm at each load level, accurately predicted by a neural network on a half-hourly basis. As opposed to the conventional approaches, this hybrid strategy can make fast decisions with less computations
Abstract: A methodology for evaluation of transient stability of medium size interconnected longitudinal power systems has been developed using a hybrid neural network/pattern recognition approach. Assessment of transient stability is done using a fast pattern recognition algorithm at each load level, accurately predicted by a neural network on a half-hourly basis. As opposed to the conventional approaches, this hybrid strategy can make fast decisions with less computations
[79] Q. Zhou, J. Davidson, and A. A. Fouad, "Application of Artificial Neural Networks in Power-System Security and Vulnerability Assessment," Ieee Transactions on Power Systems, vol. 9, no. 1, pp. 525-531, Feb.1994.
Abstract: In a companion paper the concept of system vulnerability is introduced as a new framework for power system dynamic security assessment. Using the TEF method of transient stability analysis, the energy margin DELTAV is used as an indicator of the level of security, and its sensitivity to a changing system parameter p (partial derivative DELTAV/partial derivative p) as indicator of its trend with changing system conditions. These two indicators are combined to determine the degree of system vulnerability to contingent disturbances in a stability-limited power system. Thresholds for acceptable levels of the security indicator and its trend are related to the stability limits of a critical system parameter (plant generation limits). Operating practices and policies are used to determine these thresholds. In this paper the artificial neural networks (ANNs) technique is applied to the concept of system vulnerability within the recently developed framework, for fast pattern recognition and classification of system dynamic security status. A suitable topology for the neural network is developed, and the appropriate training method and input and output signals are selected. The procedure developed is successfully applied to the IEEE 50-generator test system. Data previously obtained by heuristic techniques are used for training the ANN
Abstract: In a companion paper the concept of system vulnerability is introduced as a new framework for power system dynamic security assessment. Using the TEF method of transient stability analysis, the energy margin DELTAV is used as an indicator of the level of security, and its sensitivity to a changing system parameter p (partial derivative DELTAV/partial derivative p) as indicator of its trend with changing system conditions. These two indicators are combined to determine the degree of system vulnerability to contingent disturbances in a stability-limited power system. Thresholds for acceptable levels of the security indicator and its trend are related to the stability limits of a critical system parameter (plant generation limits). Operating practices and policies are used to determine these thresholds. In this paper the artificial neural networks (ANNs) technique is applied to the concept of system vulnerability within the recently developed framework, for fast pattern recognition and classification of system dynamic security status. A suitable topology for the neural network is developed, and the appropriate training method and input and output signals are selected. The procedure developed is successfully applied to the IEEE 50-generator test system. Data previously obtained by heuristic techniques are used for training the ANN
No comments:
Post a Comment