SIMULATION-BASED EVALUATION OF MACHINE LEARNING ALGORITHMS FOR FAULT DETECTION IN MICROGRIDS
DOI:
https://doi.org/10.55197/qjoest.v7i2.270Keywords:
microgrid protection system, fault identification, fault classification, intelligent learning algorithms, model based algorithmsAbstract
Microgrids fault detection is essential to ensure stable and uninterrupted operation, especially as renewable energy sources and distributed generation become more widespread. In this study, a single-source AC microgrid was modeled in MATLAB/Simulink to examine the effect of different short-circuit conditions, comprising Single phase to Ground, two phase, two phase to Ground and three phase/Three phase to Ground faults. By simulating these faults in different load conditions as well as different fault impedances (specifically the low impedance ranging between 0.001 and 10 Ohms) we were able to produce a dataset comprising of different features including voltages, currents, and other features extracted therein. The dataset was then utilized to test different artificial intelligence algorithms to provide a reliable basis for classification of faults and demonstrate the relative advantages of such approaches. Among the tested algorithms, Random Forest achieved the highest accuracy (82%), outperforming, Multi-Layer Perceptron, Decision Tree and long short-term memory. The future work will be extended to include high-impedance faults and real-time hardware in the loop validation, thereby contributing to the development of adaptive protection schemes for modern microgrids.
References
[1] Abdelgayed, T.S., Morsi, W.G., Sidhu, T.S. (2018): A new approach for fault classification in microgrids using optimal wavelet functions matching pursuit. – IEEE Transactions on Smart Grid 9(5): 4838-4846.
[2] Altaf, M.W., Arif, M.T., Islam, S.N., Haque, M.E. (2022): Microgrid protection challenges and mitigation approaches–A comprehensive review. – IEEE Access 10: 38895-38922.
[3] Brearley, B.J., Prabu, R.R. (2017): A review on issues and approaches for microgrid protection. – Renewable and Sustainable Energy Reviews 67: 988-997.
[4] Cano, A., Arévalo, P., Benavides, D., Jurado, F. (2024): Integrating discrete wavelet transform with neural networks and machine learning for fault detection in microgrids. – International Journal of Electrical Power & Energy Systems 155(B): 14p.
[5] Dougherty, G. (2012): Pattern recognition and classification: An introduction. – Springer, New York 196p.
[6] El-Zonkoly, A.M. (2011): Fault diagnosis in distribution networks with distributed generation. – Electric Power Systems Research 81(7): 1482-1490.
[7] Gururajapathy, S.S., Mokhlis, H., Illias, H.A. (2017): Fault location and detection techniques in power distribution systems with distributed generation: A review. – Renewable and Sustainable Energy Reviews 74: 949-958.
[8] Haykin, S. (2009): Neural networks and learning machines. – Prentice Hall 906p.
[9] Jamali, S., Ranjbar, S., Bahmanyar, A. (2020): Identification of faulted line section in microgrids using data mining method based on feature discretisation. – International Transactions on Electrical Energy Systems 30(6): 16p.
[10] Kar, S., Samantaray, S.R., Zadeh, M.D. (2017): Data-mining model based intelligent differential microgrid protection scheme. – IEEE Systems Journal 11(2): 1161-1169.
[11] Kuncheva, L.I. (2014): Combining pattern classifiers: Methods and algorithms. – John Wiley & Sons 384p.
[12] Lin, H., Sun, K., Tan, Z.H., Liu, C., Guerrero, J.M., Vasquez, J.C. (2019): Adaptive protection combined with machine learning for microgrids. – IET Generation, Transmission & Distribution 13(6): 770-779.
[13] Mishra, D.P., Samantaray, S.R., Joos, G. (2016): A combined wavelet and data-mining based intelligent protection scheme for microgrid. – IEEE Transactions on Smart Grid 7(5): 2295-2304.
[14] Paithankar, Y.G., Bhide, S.R. (2022): Fundamentals of power system protection. – PHI Learning Pvt. Ltd. 384p.
[15] Parhizi, S., Lotfi, H., Khodaei, A., Bahramirad, S. (2015): State of the art in research on microgrids: A review. – IEEE Access 3: 890-925.
[16] Rezaei, N., Uddin, M.N. (2021): An analytical review on state-of-the-art microgrid protective relaying and coordination techniques. – IEEE Transactions on Industry Applications 57(3): 2258-2273.
[17] Roy, B., Adhikari, S., Datta, S., Devi, K.J., Devi, A.D., Alsaif, F., Alsulamy, S., Ustun, T.S. (2023): Deep learning based relay for online fault detection, classification, and fault location in a grid-connected microgrid. – IEEE Access 11: 62674-62696.
[18] Saha, D., Roy, B.K.S., Das, P.N. (2019): Online adaptive protection scheme for electrical distribution network with high penetration of renewable energy sources. – Journal of Engineering Research 7(2): 242-258.
[19] Sortomme, E., Mapes, G.J., Foster, B.A., Venkata, S.S. (2008): Fault analysis and protection of a microgrid. – 40th North American Power Symposium (NAPS) 6p.
[20] Sridharan, N.V., Sugumaran, V. (2025): Visual fault detection in photovoltaic modules using decision tree algorithms with deep learning features. – Energy Sources, Part A: Recovery, Utilization, and Environmental Effects 47(2): 17p.
[21] Ton, D.T., Smith, M.A. (2012): The US Department of Energy's microgrid initiative. – The Electricity Journal 25(8): 84-94.
[22] Ustun, T.S., Ozansoy, C., Zayegh, A. (2012): Simulation of communication infrastructure of a centralized microgrid protection system based on IEC 61850-7-420. – 2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm) 6p.
[23] Veerasamy, V., Wahab, N.I.A., Othman, M.L., Padmanaban, S., Sekar, K., Ramachandran, R., Hizam, H., Vinayagam, A., Islam, M.Z. (2021): LSTM recurrent neural network classifier for high impedance fault detection in solar PV integrated power system. – IEEE Access 9: 32672-32687.
[24] Zaben, M.M., Worku, M.Y., Hassan, M.A., Abido, M.A. (2024): Machine learning methods for fault diagnosis in AC microgrids: A systematic review. – IEEE Access 12: 20260-20298.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ABDUL BASIT TAJ, SYED SAROSH ALI, ADNAN UMAR KHAN, MOIN ISLAM, SAIRA SULEMAN, MUHAMMAD HUZAIFA
This work is licensed under a Creative Commons Attribution 4.0 International License.
