Islanding Detection of Microgrid Using Decision-Tree Approach

Abstract

Microgrids are becoming more popular and irresistible options for increasing system reliability and operation. One of the most important challenges in microgrid operation is the unintentional islanding occurrence. Unintentional islanding can cause serious safety hazards and technical issues. Islanding detection methods can be classified into active and passive methods. The proposed passive approach is based on Discrete Fourier Transform and decision-tree for detecting the intentional and nonintentional microgrid islanding. The proposed microgrid islanding detection approach is tested on a microgrid equipped with synchronous generator-based DGs. The proposed method is capable of detecting islanding with a speed accuracy less than three cycles from the islanding inception. The results of proposed method are compared with other existing techniques in terms of fast islanding detection, dependability, security and accuracy. The simulation results show that the proposed approach is effective in detecting islanding phenomenon possesses compared to existing islanding detection techniques.