Title :
Online learning recurrent neural network stabilization controller for multi-machine power system
Author :
Senjyu, Tomonobu ; Yoshiteru, Morishima ; Uezato, Katsumi
Author_Institution :
Ryukyus Univ., Okinawa, Japan
Abstract :
This paper presents an online learning recurrent neural network stabilization controller to improve the transient stability of a power system. Since the proposed recurrent neural network is of the online tuning type, it can stabilize the power system for different system parameters, operating conditions, and fault point. The proposed controller robustness and effectiveness in damping power system oscillations are illustrated through simulations
Keywords :
damping; genetic algorithms; learning (artificial intelligence); neurocontrollers; oscillations; power system control; power system transient stability; recurrent neural nets; controller robustness; fault point; genetic algorithm; online learning recurrent neural network; operating conditions; power system oscillations damping; recurrent neural network stabilization controller; transient stability; Control systems; Power system control; Power system faults; Power system simulation; Power system stability; Power system transients; Power systems; Recurrent neural networks; Synchronous generators; Tuning;
Conference_Titel :
Power System Technology, 2000. Proceedings. PowerCon 2000. International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-6338-8
DOI :
10.1109/ICPST.2000.900060
