Adaptive and Self-Healing Protection Schemes for Renewable-Rich Microgrids Using Deep Reinforcement Learning
DOI:
https://doi.org/10.31185/wjes.Vol14.Iss2.785Keywords:
Reinforcement learning microgrid protection, Adaptive relaying systems, Self-healing smart grids, Fault classification and isolation, Deep reinforcement learning applications.Abstract
Integrating distributed renewable energy sources into microgrids creates new protection challenges such as bidirectional power flows, reduced fault currents, and topology changes that limit traditional relaying methods, this paper proposes a novel integrated protection framework using reinforcement learning (RL) to enable adaptive fault response and autonomous self-healing, the core innovation employs deep RL agents for two key tasks: fast and accurate fault classification and localization using raw voltage/current waveforms, and optimal service restoration via cooperative multi-agent RL that maximizes load recovery while respecting operational constraints. Experimental results show 99.9% fault classification accuracy under ideal conditions and 96.7% reliability at 20 dB noise, outperforming CNN-based methods by 12.4%, the framework reduces average outage duration from 8.7 minutes to 2.31 seconds, improving resilience and reliability for microgrids in the renewable energy era.
References
[1] M. H. Saeed, W. Fangzong, B. A. Kalwar, and S. Iqbal, "A review on microgrids' challenges & perspectives," IEEE Access, vol. 9, pp. 166502-166517, 2021.
[2] K. Kant and O. H. Gupta, "DC microgrid: A comprehensive review on protection challenges and schemes," IETE Technical Review, vol. 40, no. 4, pp. 574-590, 2023.
[3] M. Hijazi, P. Dehghanian, and S. Wang, "Transfer learning for transient stability predictions in modern power systems under enduring topological changes," IEEE Transactions on Automation Science and Engineering, vol. 21, no. 3, pp. 3274-3288, 2023.
[4] F. C. Souza Junior and H. S. Sanca, "Adaptive overcurrent protection applied to power systems with distributed generation and active network management," Journal of Control, Automation and Electrical Systems, vol. 32, no. 5, pp. 1429-1437, 2021.
[5] N. Rezaei and M. N. Uddin, "An analytical review on state-of-the-art microgrid protective relaying and coordination techniques," IEEE Transactions on Industry Applications, vol. 57, no. 3, pp. 2258-2273, 2021.
[6] A. Dagar, P. Gupta, and V. Niranjan, "Microgrid protection: A comprehensive review," Renewable and Sustainable Energy Reviews, vol. 149, p. 111401, 2021.
[7] T. A. Ahanger, M. Bhatia, and A. Aldaej, "Quantum informative analysis in smart power distribution," ACM Transactions on Intelligent Systems and Technology, vol. 15, no. 6, pp. 1-18, 2024.
[8] I. Alhamrouni, N. H. Abdul Kahar, M. Salem, M. Swadi, Y. Zahroui, D. J. Kadhim, and M. Alhuyi Nazari, "A comprehensive review on the role of artificial intelligence in power system stability, control, and protection: Insights and future directions," Applied Sciences, vol. 14, no. 14, p. 6214, 2024.
[9] S. A. Fayaz, S. Jahangeer Sidiq, M. Zaman, and M. A. Butt, "Machine learning: An introduction to reinforcement learning," Machine Learning and Data Science: Fundamentals and Applications, pp. 1-22, 2022.
[10] R. Yu, X. Zhao, S. Lu, Y. H. Chen, and C. Li, "Intelligent game-theoretic approach for resilient robust control design of cyber-physical systems: application to intelligent transportation systems," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 11, pp. 16072-16083, 2024.
[11] M. W. Altaf, M. T. Arif, S. N. Islam, and M. E. Haque, "Microgrid protection challenges and mitigation approaches–A comprehensive review," IEEE Access, vol. 10, pp. 38895-38922, 2022.
[12] M. R. K. Rachi, M. A. Khan, and I. Husain, "Local measurement-based protection coordination system for a standalone DC microgrid," IEEE Transactions on Industry Applications, vol. 57, no. 5, pp. 5332-5344, 2021.
[13] M. Castilla, M. Velasco, J. Miret, Á. Borrell, and R. Guzmán, "Control scheme for negative-sequence voltage compensation and current sharing in inverter-based grid-connected microgrids," IEEE Transactions on Power Electronics, vol. 37, no. 6, pp. 6556-6567, 2022.
[14] M. H. D. Khan, J. Imtiaz, and M. N. U. Islam, "A blockchain based secure decentralized transaction system for energy trading in microgrids," IEEE Access, vol. 11, pp. 47236-47257, 2023.
[15] G. Porawagamage, K. Dharmapala, J. S. Chaves, D. Villegas, and A. Rajapakse, "A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions," Frontiers in Smart Grids, vol. 3, p. 1371153, 2024.
[16] S. Yu, M. S. Rahman, G. Zhang, S. T. Meraj, and H. Trinh, "Comprehensive review of PMU applications in smart grid: Enhancing grid reliability and efficiency," 2025.
[17] M. Shahbazitabar, H. Abdi, H. Nourianfar, A. Anvari-Moghaddam, B. Mohammadi-Ivatloo, and N. Hatziargyriou, "An introduction to microgrids, concepts, definition, and classifications," Microgrids: Advances in Operation, Control, and Protection, pp. 3-16, 2021.
[18] N. C. Yang and J. M. Yang, "Fault classification in distribution systems using deep learning with data preprocessing methods based on fast dynamic time warping and short-time fourier transform," IEEE Access, vol. 11, pp. 63612-63622, 2023.
[19] Y. M. Nsaif, M. H. Lipu, A. Ayob, Y. Yusof, and A. Hussain, "Fault detection and protection schemes for distributed generation integrated to distribution network: Challenges and suggestions," IEEE Access, vol. 9, pp. 142693-142717, 2021.
[20] N. Giri, P. Nayak, R. K. Mallick, S. Mishra, A. Flah, H. Kraiem, and M. Kanan, "Wavelet-Based ensembled intelligent technique for a better quality of fault detection and classification in AC microgrids," Energy Conversion and Management: X, vol. 24, p. 100813, 2024.
[21] W. H. Kim, J. Y. Kim, W. K. Chae, G. Kim, and C. K. Lee, "LSTM-based fault direction estimation and protection coordination for networked distribution system," IEEE Access, vol. 10, pp. 40348-40357, 2022.
[22] K. Wang, Y. Xue, Q. Guo, M. Shahidehpour, Q. Zhou, B. Wang, and H. Sun, "A coordinated reconfiguration strategy for multi-stage resilience enhancement in integrated power distribution and heating networks," IEEE Transactions on Smart Grid, vol. 14, no. 4, pp. 2709-2722, 2022.
[23] S. Chatterjee and Y. C. Byun, "Leveraging generative adversarial networks for data augmentation to improve fault detection in wind turbines with imbalanced data," Results in Engineering, vol. 25, p. 103991, 2025.
[24] S. Stock, D. Babazadeh, C. Becker, and S. Chatzivasileiadis, "Bayesian physics-informed neural networks for system identification of inverter-dominated power systems," Electric Power Systems Research, vol. 235, p. 110860, 2024.
[25] B. Wang, A. Baziar, and M. Askari, "A deep reinforcement learning framework for adaptive resiliency enhancement in smart power grids," IEEE Access, 2025.
[26] M. Laurelli, "Adaptive meta-domain transfer learning (AMDTL): A novel approach for knowledge transfer in AI," arXiv preprint arXiv:2409.06800, 2024.
[27] R. Azizi and S. Seker, "Microgrid fault detection and classification based on the boosting ensemble method with the Hilbert-Huang transform," IEEE Transactions on Power Delivery, vol. 37, no. 3, pp. 2289-2300, 2021.
[28] G. S. Carvalho, A. R. Almeida, D. D. Ferreira, B. F. dos Santos Jr, L. H. P. Vasconcelos, and D. de Oliveira Sobreira, "High-impedance fault modeling and classification in power distribution networks," Electric Power Systems Research, vol. 204, p. 107676, 2022.
[29] R. A. Jacob, S. Paul, S. Chowdhury, Y. R. Gel, and J. Zhang, "Real-time outage management in active distribution networks using reinforcement learning over graphs," Nature Communications, vol. 15, no. 1, p. 4766, 2024.
[30] M. Kaheni, J. Fu, and A. V. Papadopoulos, "Rule-based predictive control for battery scheduling in microgrids under power generation and load uncertainties," IEEE Transactions on Automation Science and Engineering, 2024.
[31] R. Yan, Y. Yuan, Z. Wang, G. Geng, and Q. Jiang, "Active distribution system synthesis via unbalanced graph generative adversarial network," IEEE Transactions on Power Systems, vol. 38, no. 5, pp. 4293-4307, 2022.
[32] J. Vasquez, M. Jaramillo, and D. Carrión, "An intelligent framework for multiscale detection of power system events using Hilbert–Huang decomposition and neural classifiers," Applied Sciences, vol. 15, no. 12, p. 6404, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hussein Naeem Qasim
This work is licensed under a Creative Commons Attribution 4.0 International License.
