An Intelligent Method of Anti Islanding Detection using ANN

Abstract

A new method of anti-islanding detection in a Microgrid using Artificial Neural Network (ANN) with Daubechies 4 type mother wavelet which is decomposed into five level wavelets is discussed in this paper. The Microgrid discussed here comprises of a Photovoltaic system, Wind Energy Conversion System (WECS), Solid Oxide Fuel Cell (SOFC) with a battery along with linear and non-linear loads. The potential difference in the PCC along with current waveform at the same point is used for detection of islanding. The system is studied under different fault conditions and the results are discussed. Signals such as Energy levels and SD of the extracted signals at the point of common coupling both under faulty and normal operating condition are used to train the neural network. MATLAB Simulink and M file is used for the analysis of this system at various conditions.