Neural Network Based Control Strategy for Hybrid DSTATCOM in Three Phase Four Wire Distribution System Under Non-Ideal Voltage Source Conditions and Varying Load Conditions

Abstract

In this paper the choice of power quality compensator is a DSTATCOM which constitutes a four leg voltage source converter (VSC) and a DC capacitor. An artificial neural network (ANN) based synchronous reference frame (SRF) theory is proposed for the generation of gating pulse of the DSTATCOM to balance the source current, eliminate harmonics and to compensate neutral current and reactive power in three phase four wire (3P4W) distribution system. In the proposed control strategy ANN controllers replace the PI controllers and low pass filters of conventional method. ANN controllers are also implemented to keep up the voltage across the capacitor and as a compensator to compensate neutral current under unbalanced load conditions. Various transformer topologies are simulated and compared with the proposed control strategy for compensation of neutral current. The DSTATCOM performance is adjudged under balanced, unbalanced and/or distorted voltage source conditions through simulation using MATLAB software. Data extracted from the experiment conducted in the laboratory to study the effect of non-linear load are used in the simulation to prove the efficacy of the proposed control strategy in power quality improvement.