Review On Machine Learning-Based Adaptive Protection Scheme For Distribution Side Relay Coordination
Keywords:
Artificial Neural Networks, Support Vector Machines, MG (micro grid)Abstract
The increasing penetration of distributed energy resources, renewable energy systems, electric vehicles, and intelligent loads has significantly increased the complexity of modern power distribution networks. Consequently, conventional relay coordination techniques based on fixed settings face challenges in maintaining reliable, selective, and fast protection under varying operating conditions. Recent advances in Artificial Intelligence (AI) and Machine Learning (ML) have introduced adaptive protection strategies capable of improving fault detection, classification, and relay coordination performance. This review paper presents a comprehensive analysis of machine learning-based adaptive protection schemes for distribution-side relay coordination, with particular emphasis on Artificial Neural Networks (ANN) and Support Vector Machines (SVM). Various fault classification techniques, including single line-to-ground (SLG), line-to-line (LL), double line-to-ground (DLG), and three-phase (LLL) faults, are reviewed using electrical parameters such as voltage, current, impedance, and fault location as input features.
References
Sheta, A. N., Sedhom, B. E., Pal, A., El Moursi, M. S., & Eladl, A. A. (2024). Machine-learning-based adaptive settings of directional overcurrent relays with double-inverse characteristics for stable operation of microgrids. IEEE Transactions on Industrial Informatics, 21(1), 584-593.
Al-Bhadely, F., & Inan, A. (2024). An innovative approach for enhancing relay coordination in distribution systems through online adaptive strategies utilizing dnn machine learning and a hybrid ga-sqp framework. Arabian Journal for Science and Engineering, 49(12), 16865-16887.
Elhaffar, A., El-Naily, N., & Mansouri, M. (2025). Adaptive Clustering and Optimization With Hardware-in-the-Loop Validation for Enhanced Overcurrent Relay Protection in Power Distribution Networks. IEEE Access.
Chen, Y., & Zhang, S. (2025). The communication-oriented evolution of power system relay protection: Key technologies and frontier development trends. Advances in Resources Research, 5(4), 2483-2527.
Rahman, Z. A. (2026). Resilient Cascade Mitigation in Smart Grids Using Federated Deep Reinforcement Learning for Cooperative, Privacy-Preserving Relay Protection Schemes. Muthanna Journal of Engineering and Technology, 14(2).
Ruiyi, C., Rui, G., Qisheng, L., Xingwang, J., Ling, S., Guanbao, Z., & Jia, H. (2025, April). Analysis of an IoT-Based Multi-Agent Relay Protection System and Cooperative Control Strategies. In 2025 10th Asia Conference on Power and Electrical Engineering (ACPEE) (pp. 1093-1097). IEEE.
Mayangsari, D. R. K., & Khayam, U. (2025). Trends and Challenges in AI-Driven Relay Coordination for Distribution Networks with Multi-DER: A Systematic Literature Review. Available at SSRN 5339644.
Wu, D., Yu, X., & Liao, Y. (2025, January). Adaptive protection scheme in modern distribution networks based on proximal policy optimization. In 18th International Conference on Developments in Power System Protection (DPSP APAC 2025) (Vol. 2025, pp. 70-74). IET.
Prasad, U., Mohanty, S. R., Singh, S. P., & Jagan, A. (2024). Robust centralized protection scheme with AI-based fault diagnosis capabilities for graph-structured AC microgrids. IEEE Transactions on Smart Grid, 16(2), 1975-1992.
Alamshah, A., Ramli, S. P., Mansor, N. N., Usama, M., Mokhlis, H., Suyono, H., & Hasanah, R. N. (2024). Recent developments of directional overcurrent relay coordination in ring distribution network based on hybrid optimization techniques. IEEE Access, 13, 14961-14982.
Drul, H. (2026). Reinforcement Learning, Demand Response, and Protection in Active Distribution Networks: A State-of-the-Art Review. Demand Response, and Protection in Active Distribution Networks: A State-of-the-Art Review (March 12, 2026).
Yazdaninejadi, A., Ebrahimi, H., & Golshannavaz, S. (2025). An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach. IEEE Access.
Fu, K., Li, M., Li, C., Zhu, K., Zou, L., & Long, Y. (2024, May). Research on Adaptive Control of Relay Protection Based on Machine Learning in Smart Grid. In 2024 IEEE 4th International Conference on Electronic Technology, Communication and Information (ICETCI) (pp. 1123-1127). IEEE.
Uddin, M. N., Rezaei, N., & Arifin, M. S. (2023). Hybrid machine learning-based intelligent distance protection and control schemes with fault and zonal classification capabilities for grid-connected wind farms. IEEE Transactions on Industry Applications, 59(6), 7328-7340.
Al-Saadi, M., Al-Greer, M., & Short, M. (2023). Reinforcement learning-based intelligent control strategies for optimal power management in advanced power distribution systems: A survey. Energies, 16(4), 1608.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
