Dynamic identification and control of PWM inverter VAr compensator using neural network

Abstract

The performance and dynamic characteristic of a solid-state VAr compensator controlled by a neural network is presented and analyzed. Neural network based indirect model reference adaptive control (NN-MRAC) theory is used to design the multioutput nonlinear controller structure. Simulation results of the closed loop control system using a multioutput nonlinear neural network controller demonstrate desirable reactive power compensation and voltage regulation.