Artificial Neural Network based Shunt Active Power Filter

Abstract

A reliable and efficient adaptive neural network based neural network based active filter to estimate and compensate harmonic distribution from an AC line is discussed in this report. Now-a-days it is observed that there is drastic rise of cur- rent and voltage harmonics in power systems, caused by nonlinear loads results in harmonic contamination. The power filters, generally Active Power Filters (APFs) are generally used to correct the load power factor by compensating the harmonics. Artificial intelligence (AI) techniques that majorly includes artificial neural networks, are recently having major impact on motor drives and power electronics. Neural networks have generated a new edge in power electronics, which is already a complex and advanced technology that is going through an active evolution in the recent years. This report gives complete information of neural network applications in the intelligent control and estimation for power quality compensation. The real-life applications of neural networks till date include robotics, data processing, function approximation or regression analysis and computer numerical control. This report focuses on implementing the aforementioned technology to improve the quality of power transmission and distribution.