Optimization control of STATCOM in power system with Adaptive Critic Designs

Abstract

This paper presents a novel nonlinear optimal neurocontroller for a static compensator (STATCOM) connected to a power system. The design for the optimal controller is based on a class of Adaptive Critic Designs (ACDs) called the Action Dependant Heuristic Dynamic Programming (ADHDP). The ADHDP class of ACDs uses two neural networks, an “Action” network (which actually sends the control signals) and a “Critic” network (which critics the action network performance). The optimal control policy is evolved by the action network over a period of time using the feedback signals provided by the critic network. A series of simulations on STATCOM connected to a single machine infinite bus system with proposed neurocontroller and conventional PI controller were carried out in MATLAB/SIMULINK. Results are presented to show that the ADHDP-based neurocontroller performs better than the conventional PI controller, especially when the system conditions and configuration were changed. The numerical simulation results of using this method in one STATCOM connected to power system show that the control scheme can maintain voltage at load bus and prevent the occurrence of voltage collapse when the large disturbances occur.