Comparison of PI and neural network based controllers for shunt active power filter

Shunt active power filter, when used with non linear loads, provides an elegant solution to reactive power compensation as well as harmonic mitigation, leading to improvement in power quality. The present study deals with Neuro based controllers viz. neural network (NN) control and neuro fuzzy (NF) control for shunt active power filter. Their superiority over PI type of controller is demonstrated through extensive simulation results.