Artificial Intelligence Based Controller for Series and Shunt Active Filters for Power Quality Improvement

Abstract

Neural network based p-q theory control strategy for shunt active power filter and neural network based synchronous reference frame (SRF) theory control strategy for series active power filter are proposed in this paper to compensate power quality issues related to current and voltage respectively through Unified Power Quality Conditioner (UPQC) in three phase four wire (3P4W) distribution system for various balanced/unbalanced loads and balanced /unbalanced/ distorted source conditions. The Artificial Neural Network (ANN) controllers are designed to replace the low pass filters (LPF) and proportional-integral controllers of the conventional control strategy. ANN controllers are also implemented to maintain voltage across the capacitor and as a compensator to compensate neutral current under varying conditions of source and load. The proposed control strategies mitigate harmonic/reactive currents and voltage harmonics, ensure balanced and sinusoidal source current from the supply mains that are nearly in phase with the supply voltage. The performance of the UPQC with proposed ANN controllers is validated and investigated through simulations using MATLAB software. The simulation results prove the efficacy of the proposed neural network based control strategy under varying source and load conditions.