Application of neural networks in power quality

Use of power electronic converters with nonlinear loads produces harmonic currents and reactive power. A shunt active power filter provides an elegant solution to reactive power compensation as well as harmonic mitigation leading to improvement in power quality. However, the shunt active power filter with PI type of controller is suitable only for a given load. If the load is varying, the proportional and integral gains are required to be fine tuned for each load setting. The present study deals with neural network based controller for shunt active power filter. The performance of neural network controller evaluated and compared with PI controller.