A novel SVM based adaptive scheme for accurate fault identification in microgrid

Microgrids, which include distributed energy resources, provide a more reliable power supply. However, despite the fast advancements in microgrid protection, the microgrid's dynamic behaviour challenges the protection. The large-scale integration of renewable energy sources (RES) and the addition of electric vehicle (EV) charging loads cause additional protection issues on the grid due to its volatile nature. Conventional fault prediction schemes do not provide reliable protection with the dynamic nature of microgrids. This article proposes an adaptive scheme that accurately detects the volatile changes in the microgrid under normal and fault conditions. The novelty of the proposed approach is that the general-purpose adaptive scheme is based on a two-level SVM classifier model to ensure accuracy and speed of operation. The SVM-1 model identifies the mode of operation, the variations in RES generation, the random addition of EV charging load, and the occurrence of a fault in the microgrid. SVM-2 identifies the exact type and location of fault that occurred. The SVM model uses RMS values of three-phase voltage and current measurements as data inputs. The efficacy of the proposed scheme is tested on an IEEE 9-bus microgrid test bed by simulation experiments using MATLAB/SIMULINK. The sensitivity analysis results prove the robustness of the proposed scheme. Moreover, the proposed method is validated using real-time experiments on Hardware-In-Loop (HIL) real-time simulator, OPAL-RT, and Raspberry Pi microcontroller. Accurate online detection of faulted lines and fault types is obtained within a cycle of AC in grid-connected and islanded modes of operation.