Optimal Variable-Gain Neural Network-Based UPFC Controller by Means of Differential Evolution Algorithm

This paper presents a modified control strategy for a Unified Power flow Controller (UPFC). UPFC is one of the most promising FACTS devices to control power system oscillations and enhancing the transient stability. Power systems, always contains parametric uncertainties which must be considered in controller designs. Variations of power system operating conditions could move parameter region of UPFC controllers in its parameter space. Focus of present study is to investigate two main functions: (1) prevent interactions caused by inappropriate setting of UPFC controller's parameters by using differential evolution algorithm; (2) how to conclude the optimized controller's parameters in the model preventing delays caused by DEA slow convergence response. In this paper, a novel gain-varied control for UPFC based on artificial neural network (ANN) and k-means clustering algorithm is proposed and compared with a conventional PI controller. Simulation results developed in MATLAB-SIMULINK environment verify the viability and effectiveness of proposed control scheme in comparison with conventional PI controller. Copyright (C) 2010 Praise Worthy Prize S.r.l. - All rights reserved.