PSO-BASED LEARNING OF SUPPORT VECTOR MACHINES FOR ADAPTIVE TCSC

摘要

This paper proposes the design of an adaptive thyristor controlled series capacitor (TCSC) using support vector machines (SVMs) and particle swarm optimization (PSO). The SVMs for an adaptive TCSC are trained by the data obtained from a multi-machine power system. PSO is used to optimize the SVM parameters based on k-fold cross-validation technique. The TCSC parameters produced by SVMs can be adapted by various operating conditions. Simulation results in a two-area four-machine power system demonstrate that the proposed SVMs for an adaptive TCSC is much superior to the conventional TCSC with fixed parameters under various operating conditions.