SIMULATION-BASED EVALUATION OF MACHINE LEARNING ALGORITHMS FOR FAULT DETECTION IN MICROGRIDS
This paper presents a simulation-based analysis of fault detection in alternating current microgrids through data-driven methods. A detailed simulation-based microgrid model is created for conducting the fault analysis, including single phase ground fault, line fault, two phase fault and three phase fault situations. Simulations were carried out under different loading conditions and fault impedance values to obtain an extensive set of data containing voltage, current, and signal characteristics. This data was used to test the performance of various machine learning techniques for fault classification. The results show that the ensemble methods perform better than standalone models, with Random Forest (RF) demonstrating the highest classification performance. This findings of this research underscore the potential of data-driven techniques in improving the robustness and flexibility of AC protection systems in contemporary microgrids. Future work will focus on extending the analysis to more complex fault conditions and validating the proposed approach through real-time implementation.