Islanding detection in a distribution network with distributed generators using signal processing techniques

This paper proposes an accurate and fast islanding detection technique for a distribution network with distributed generators (DGs). Two signal processing techniques based islanding detection is proposed in this paper, one is based on discrete wavelet transform (DWT) with artificial neural network (ANN), and the another one is based on S-transform with ANN. The negative sequence voltage/current signals are retrieved at the targeted DG location are used for islanding detection in the distribution system. In this paper, the wavelet and S-transforms are used for fault location and classification applications. Here, the feature extraction is used for reducing the dimension of large data set by converting it into set of features. In this work, particle swarm optimization (PSO) based feature selection technique is used. The simulation results on test system show the effectiveness of proposed islanding detection techniques.