Power conditioning in distribution systems using ANN controlled Shunt Hybrid Active Power Filter

Abstract

This paper focuses on an Artificial Neural Network (ANN) controller based Shunt Hybrid Active Power Filter (SHAPF) for compensating the harmonics of the distribution system. To enhance the performance of the conventional controller (Hysteresis controller) and to take advantage of intelligent controllers, a back propagation algorithm based feed forward-type ANN technique is implemented in shunt active power filter for producing the controlled pulses required for IGBT inverter. The proposed approach mainly work on the principle of energy stored by capacitor 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 complete power system set model of the proposed filter technique has been developed in MATLAB. The control algorithm developed is very simple. Simulations are carried out for the proposed scheme 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.