Voltage Balancing Using Particle Swarm Optimization and Support Vector Machine

Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) are proposed in this paper to provide an intelligent integrated solution for controlling reactive power and restoring voltage balance in a three-phase power system. The PSO algorithm is used in offline mode to determine the optimal set of firing angles for the Thyristor-Controlled-Reactor compensator according to the smallest fitness value required for voltage balancing. SVM are presented as online mode controllers for quickly and precisely restoring voltage balance. The optimum firing angles obtained by PSO are used to train the SVM. The SVM models are finally used as real-time controllers to retrieve the voltage balance in online mode. A simulation model and experimental setup of the electrical power system are built. Several simulations and practical case studies have been conducted to test and validate the capability of the proposed approach in solving the voltage unbalance problem. The results indicated the proposed approach's superior capacity to restore voltage balance rapidly.