Comparison of Adaptive Neuro-Control System and Self-Tuning Regulator for Generator Excitation Control from a Viewpoint of Stability Enhancement

Abstract

The authors proposed a nonlinear adaptive generator control system with neural networks for improving damp-ing of power systems and showed its effectiveness in a one-machine infinite bus test power system in their previous paper. The proposed neuro-control system has a similar system structure to that of self-tuning regulators based on adaptive control theory and it works adaptively with a performance index similar to that of linear optimal regulators based on optimal control theory.
In this paper, a self-tuning regulator for generator excitation control is designed in order to be compared with the proposed neuro-control system. Through digital time simulations in a one-machine infinite bus test power system, the control performance of both methods is discussed. As a result, the proposed adaptive neuro-control system improves the system damping more effectively than the self-tuning regulator. It is mainly because the nonlinear characteristics of neural networks in the proposed neuro-control system work effectively while the self-tuning regulator is linear in nature.