Online Learning Neural Network based PSS with Adaptive Training Parameters

This paper provides a new method to improve power system stability using recurrent neural network with adaptive training parameters. Power system generators are equipped with automatic voltage regulator, power system stabilizer, and governor to control and stabilize the system. The controller parameters are tuned using mathematical methods, or heuristic search methods such as genetic algorithm. Therefore these control parameters are often fixed and are set for particular system configurations or operating points. Artificial neural network can be tuned for changing system conditions and thus provide better control. Artificial neural network is used in this paper in parallel with the existing PSS to effectively damp the oscillations and improve overall system performance. Online training method is employed with multilayer recurrent neural network. Training is based on back propagation with adaptive training parameters. This controller is tested on two different systems and simulation results are presented to illustrate the proposed approach.

[1]  L. Guan,et al.  Artificial neural network power system stabiliser trained with an improved BP algorithm , 1996 .

[2]  P. Kundur,et al.  Application of Power System Stabilizers for Enhancement of Overall System Stability , 1989, IEEE Power Engineering Review.

[3]  A. Feliachi,et al.  Decentralized extended-backstepping control of power systems , 2006, 2006 IEEE Power Engineering Society General Meeting.

[4]  H. Happ.  Power system control and stability , 1979, Proceedings of the IEEE.

[5]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[6]  Lin Guan,et al.  AN ON-LINE SELF-LEARNING POWER SYSTEM STA USING A NEURAL NETWORK METH , 1997 .

[7]  Lin Guan,et al.  An on-line self-learning power system stabilizer using a neural network method , 1997 .

[8]  Ieee Standards Board.  IEEE recommended practice for excitation system models for power system stability studies , 1992 .

[9]  Om P. Malik,et al.  Application of neural adaptive power system stabilizer in a multi-machine power system , 1999 .

[10]  A. Feliachi,et al.  PAT: A Power Analysis Toolbox for MATLAB/Simulink , 2002, IEEE Power Engineering Review.

[11]  K. Uezato,et al.  Online learning recurrent neural network stabilization controller for multi-machine power system , 2000, PowerCon 2000. 2000 International Conference on Power System Technology. Proceedings (Cat. No.00EX409).

[12]  A. Feliachi,et al.  Genetic algorithm based inter-area oscillation damping controller design using MATLAB , 2002, IEEE Power Engineering Society Summer Meeting,.

[13]  A. Feliachi,et al.  Power system stability enhancement using backstepping controller tuned by particle swarm optimization technique , 2005, IEEE Power Engineering Society General Meeting, 2005.