Islanding Detection of Distribution Generator in Microgrid System

Distributed Generation (DG,) is a new source which is used in distribution systems. DGs are connected directly by distribution system operators or indirectly by customers. The DGs usually are connected near the consumer load centers. The high use of DGs leads to improvement of power quality, improvement of voltage profile, a decrease of losses. Due to the increasing need to distributed energy resources in power systems, their problems should be studied. One of the main problems of distributed energy resources is unplanned islanding. The unplanned islanding has some dangers to the power systems and the repairman which are works with the incorrect devices. The proposed method is based on wavelet transform and a new classifier named as Artificial Neural Network (ANN) and Support Vector Machine (SVM). The proposed method is implemented on a 14 IEEE bus grid in MATLAB/SIMULINK software. The results show the high accuracy of islanding detection of the proposed method. In this paper, five generator as wind turbine is assumed as a distributed resource. At last, comparison of ANN and SVM are compared and finally conclusion provide for best classifier for islanding detection for distributed generator system.