Deep Learning based Relay for Online Fault detection, classification, and fault location in a grid-connected Microgrid

In this article, a maiden attempt have been taken for the online detection of faults, classification and identification fault locations grid-connected Micro-grid (MG) system. A deep learning algorithm-based Long Short Term Memory (LSTM) network is proposed, first time, faults their classifications considered MG system to overcome issues that persist in existing algorithms. Also, combination an LSTM feed-forward neural (FFNN) with back-propagation algorithm (BPA) proposed identify exact since more challenging than categorizations. To select suitable multiple hidden layers achieving aforesaid objectives, rigorous analysis has done. study accuracy techniques, different types parameters are paper. An extensive simulation done MATLAB/Simulink platform performance techniques. validate effectiveness entire implemented real-time using OPAL-RT digital simulator. Comparison also results obtained ANN The show techniques based on effectively detect, classify, location acceptable performances.