A Deep learning approach for Islanding Detection of Integrated DG with CWT and CNN
Ch. Rami Reddy, K. Harinadha Reddy, B. Srikanth Goud, B. Pakkiraiah
Abstract
The ever increasing demand of electricity leads to the advancement of Distributed Generation (DG). Almost the DG sources are renewable in nature. One of the major complications with high penetration of DG sources is islanding. The islanding may damage the clients and their equipment. As per the IEEE 1547 DG interconnection standards, the islanding will be identified in a period of two seconds and the DG must be turned off. In this paper an advanced islanding detection process stand on deep learning technique with Continuous Wavelet Transforms (CWT) and Convolution Neural Networks (CNN) is implemented. This approach basically transforms the time series information into scalogram images, later the images are used to train and to test the islanding and non islanding events. The outcomes are correlated with the Artificial Neural Networks (ANN) and Fuzzy logic methods. The comparison shows that the proposed deep learning approach efficiently detects the islanding and non islanding events.