Artificial Neural Network Control Strategy for Multi-converter Unified Power Quality Conditioner for Power Quality Improvements in 3-Feeder System

This paper presents about the power quality improvements of the 3-feeder system using the multi-converter unified power quality conditioner (MC-UPQC) based on voltage source converters in which the DC link is common. The control strategy for the converter is based on the artificial neural network (ANN) by using the Levenberg–Marquardt back-propagation algorithm for mitigation of the sag, swell, and unbalance in the system and maintaining the system voltage profile. The pulse generation is based on the hysteresis loop by comparing the error signals. The performance analysis of the MC-UPQC using neural network as control strategy is verified using the MATLAB/SIMULINK.