Harmonic reduction technique in PWM AC voltage controller using Particle Swarm Optimization and artificial neural network

This paper proposes a novel harmonic reduction technique for designing a Pulse Width Modulation (PWM) AC voltage controller. In the proposed technique, Total Current Harmonic Distortion (THDi), subjected to be minimized, is formulated in a cost function in an optimization problem; the optimal turn on and turn off angles in PWM waveform for a given output voltage are evaluated by Particle Swarm Optimization (PSO) technique. To apply our proposed technique for all output voltages, artificial neural network (ANN) is investigated to approximate the switching angles from sets of optimal angles evolved by PSO. Simulation results show that the proposed technique is suited for designing and gains a better performance compared to the conventional technique.