Power Quality Improvement in Distribution System using ANN Based Shunt Active Power Filter

Abstract

This paper focuses on an Artificial Neural Network (ANN) controller based Shunt Active Power Filter (SAPF) for mitigating the harmonics of the distribution system. To increase the performance of the conventional controller and take advantage of smart controllers, a feed forward-type (trained by a back propagation algorithm) ANN-based technique is implemented in shunt active power filters for producing the controlled pulses required for IGBT inverter. The proposed approach mainly work on the principle of capacitor energy to maintain the DC link voltage of a shunt connected filter and thus reduces the transient response time when there is abrupt variation in the load. The entire power system block set model of the proposed scheme has been developed in MATLAB environment. Simulations are carried out by using MATLAB, it is noticed that the %THD is reduced to 2.27% from 29.71% by ANN controlled filter. The simulated experimental results also show that the novel control method is not only easy to be computed and implemented, but also very successful in reducing harmonics.