Fault Detection and Location In DC Microgrids by Recurrent Neural Networks and Decision Tree Classifier

Microgrids have played an important role in distribution networks during recent years. DC microgrids are very popular among researchers because of their benefits. However, protection is one of the significant challenges in the way of these microgrids progress. As a result, in this paper, a fault detection and location scheme for DC microgrids is proposed. Due to advances in Artificial Intelligence (AI) and the suitable performance of smart protection methods in AC microgrids, Recurrent Neural Networks (RNNs) are used in the proposed method to locate faults in DC microgrids. In this method, fault detection and location are done by measuring feeders current and main bus voltage. Furthermore, the performance of the proposed method is assessed in grid-connected and the islanded operation modes of the microgrid. The result has confirmed the efficiency of the proposed scheme . In this paper, MATLAB and DIgSILENT are used to design RNNs and DC microgrid simulation respectively.