Neural learning algorithm based power quality enhancement for three phase three wire distribution system utilizing shunt active power filter strategy

• Published in: 2011 International Conference on Power and Energy Systems pp. 1 - 6
• Main Authors: Kumar, A. S., Raj, P. A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2011
• Subjects: Active filters; Harmonic analysis; Joining processes; Neural Learning Algorithm; Power Factor; Power harmonic filters; Power quality; Reactive power; Real Power; Total Harmonic Distortion; True Power; Voltage control
• DOI: 10.1109/ICPES.2011.6156667

This paper explores the application of artificial intelligence on solving the power quality problems by using the shunt active power filter strategy for three phase three wire distribution system. The unit vector template generation control technique is modeled as current controller for the shunt active power filter strategy. The proportional and integral (PI) controller is designed to minimize error between the actual and the reference DC voltage of shunt active power filter strategy. The transient period and peak overshoot of DC bus voltage using a PI controller is observed to be higher in initial and load change conditions. The artificial neural network is a powerful tool used to generate the current signal with very low oscillation and faster settling time. In this paper, a new neural learning algorithm (NAL) is proposed for the current controller of the shunt active power filter strategy. The performance of the proposed neural learning algorithm is extensively analyzed of diode rectifier RL non linear load with respect to two different operating conditions. The proposed system is designed with MATLAB/Simulink environment.