Fast voltage estimation using an artificial neural network

Abstract Fast estimation of bus voltages is important for contingency analysis and security assessment of a power system. In this paper, an approach based on artificial neural networks (ANNs) is presented to estimate bus voltages in a very efficient manner. In the design of the ANN, a set of system variables which affect bus voltages most are first selected as the inputs to the ANN using an entropy function. A number of training patterns are then created to train the ANN. The resultant ANN is applied to estimate bus voltages following an outage event in a 30-bus system and in the Taiwan power system. Since accurate bus voltage predictions can be achieved very quickly by the proposed method, it is expected that the developed ANN can provide valuable information for operators in real-time system operation.

[1]  John Zaborszky,et al.  Fast Contingency Evaluation Using Concentric Relaxation , 1980, IEEE Transactions on Power Apparatus and Systems.

[2]  A. Kishore,et al.  Static Optimization of Reactive Power Sources by use of Sensitivity Parameters , 1971 .

[3]  Antti J. Koivo,et al.  Security Evaluation in Power Systems Using Pattern Recognition , 1974 .

[4]  Y.-Y. Hsu,et al.  Short term load forecasting using a multilayer neural network with an adaptive learning algorithm , 1992 .

[5]  T. S. Chung,et al.  Application of pattern recognition technique to power system security analysis and optimization , 1990 .

[6]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[7]  R.J. Marks,et al.  Preliminary results on using artificial neural networks for security assessment (of power systems) , 1989, Conference Papers Power Industry Computer Application Conference.

[8]  Chao-Rong Chen,et al.  Tuning of power system stabilizers using an artificial neural network , 1991 .

[9]  Yuan-Yih Hsu,et al.  Voltage control using a combined integer linear programming and rule-based approach , 1992 .

[10]  Arun Phadke,et al.  Redistribution of Reactive Power Flow in Contingency Studies , 1986, IEEE Transactions on Power Systems.

[11]  Y. Hsu,et al.  Fuzzy-set based contingency ranking , 1992 .

[12]  J.-C. Chow,et al.  Screening power system contingencies using a back-propagation trained multiperceptron , 1989, IEEE International Symposium on Circuits and Systems,.

[13]  R. D. Shultz,et al.  A Power System Operator Emulator--the Security Assessment Task , 1985, IEEE Transactions on Power Apparatus and Systems.

[14]  Dejan J. Sobajic,et al.  Artificial Neural-Net Based Dynamic Security Assessment for Electric Power Systems , 1989, IEEE Power Engineering Review.

[15]  Antti J. Koivo,et al.  Application of Pattern Recognition to Steady-State Security Evaluation in a Power System , 1973, IEEE Trans. Syst. Man Cybern..

[16]  A. Bose,et al.  An adaptive pre-filter for the voltage contingency selection function , 1989, Conference Papers Power Industry Computer Application Conference.

[17]  O. Alsac,et al.  Security analysis and optimization , 1987, Proceedings of the IEEE.

[18]  C. S. Chang.  Fast power system voltage prediction using knowledge-based approach and on-line box data creation , 1989 .

[19]  T. Tsuji,et al.  Security monitoring systems including fast transient stability studies , 1975, IEEE Transactions on Power Apparatus and Systems.

[20]  Jay S. Patel,et al.  Factors influencing learning by backpropagation , 1988, IEEE 1988 International Conference on Neural Networks.

[21]  C. Martinez,et al.  Reactive Switching Simulation in Security Analysis At Florida Power and Light System Control Center , 1985, IEEE Transactions on Power Apparatus and Systems.

[22]  K. Mamandur.  Emergency Adjustments to Var Control Variables to Alleviate Over-Voltages, Under-Voltages,and Generator Var Limit Violations , 1982, IEEE Transactions on Power Apparatus and Systems.

[23]  Dejan J. Sobajic,et al.  An artificial intelligence system for power system contingency screening , 1988 .

[24]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[25]  R.J. Marks,et al.  Artificial neural networks for power system static security assessment , 1989, IEEE International Symposium on Circuits and Systems,.

[26]  S.N. Talukdar,et al.  CQR: a hybrid expert system for security assessment (of power systems) , 1989, Conference Papers Power Industry Computer Application Conference.

[27]  R.J.F. Dow,et al.  Neural net pruning-why and how , 1988, IEEE 1988 International Conference on Neural Networks.

[28]  A. Bose,et al.  Reactive Power Considerations in Automatic Contingency Selection , 1982, IEEE Transactions on Power Apparatus and Systems.

[29]  V. Brandwajn,et al.  Efficient bounding method for linear contingency analysis , 1988 .

[30]  Richard W. Hamming,et al.  Coding and Information Theory , 1980 .

[31]  Norio Baba,et al.  A new approach for finding the global minimum of error function of neural networks , 1989, Neural Networks.

[32]  Nanming Chen,et al.  Distribution factors of reactive power flow in transmission line and transformer outage studies , 1992 .

[33]  Chao-Rong Chen,et al.  Synchronous machine steady-state stability analysis using an artificial neural network , 1991 .

[34]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[35]  Allen J. Wood,et al.  Power Generation, Operation, and Control , 1984 .

[36]  E. McClelland,et al.  Fast Voltage Prediction Using a Knowledge Based Approach , 1983, IEEE Transactions on Power Apparatus and Systems.