Study the Robustness of Automatic Voltage Regulator for Synchronous Generator Based on Neural Network

Abstract

Abstract – Artificial Neural Networks (ANN) can be used as intelligent controllers tocontrol non-linear dynamic systems through learning, which can easily accommodatethe non linearity’s, time dependencies, model uncertainty and external disturbances.Modern power systems are complex and non-linear and their operating conditions canvary over a wide range. The Nonlinear Auto-Regressive Moving Average (NARMAL2)model system is proposed as an effective neural networks controller model toachieve the desired robust Automatic Voltage Regulator (AVR) for SynchronousGenerator (SG) to maintain constant terminal voltage. The concerned neural networkscontroller for AVR is examined on different models of SG and loads. The results showsthat the neuro-controllers have excellent responses for all SG models and loads in viewpoint of transient response and system stability compared with conventional PIDcontrollers. Also shows that the margins of robustness for neuro-controller are greaterthan PID controller.