《Neural network based decentralized excitation control of lar》.pdf

2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006 Neural Network based Decentralized Excitation Control of Large Scale Power Systems 1 2 Wenxin Liu , Member, IEEE , Jagannathan Sarangapani , Senior Member, IEEE, 2 2 Ganesh K. Venayagamoorthy , Senior Member, IEEE, Donald C. Wunsch II , Fellow, IEEE, and David A. Cartes1, Member, IEEE nonlinear multimachine power system models [1, 2]. However, Abstract—This paper presents a neural network (NN) based differential geometric based nonlinear controller designs decentralized excitation controller design for large scale power require the exact knowledge of the system dynamics. Imprecise systems. The proposed controller design considers not only the knowledge will degrade the performance of the controller dynamics of generators but also the algebraic constraints of the designs. Since it is impossible to make the assumption that the power flow equations. The control signals are calculated using complex power system dynamics can be known accurately, only local signals. The transient stability and the coordination of these controller designs cannot be widely accepted. the subsystem controllers can be gua