AI-Driven Protection Schemes for Modern Power Grids: Technologies, Challenges, and Opportunities

Document Type : Review article

Authors

1 Electricity distribution company of Chaharmahal and Bakhtiari province ,Shahrekord, Iran

2 National University of Skills, Chaharmahal and Bakhtiari, Shahrekord, Iran.

Abstract

The rapid evolution of modern power grids, driven by the large-scale integration of intermittent renewable energy sources, distributed generation, and power electronic interfaces, has significantly challenged the effectiveness of conventional threshold-based protection schemes. Traditional systems often exhibit limited performance under dynamic fault currents, evolving network topologies, and complex transients, increasing the risk of maloperation and reduced system resilience. In this context, Artificial Intelligence (AI) has emerged as a promising data-driven paradigm to enhance the intelligence and reliability of grid protection. This paper presents a comprehensive review of AI-driven protection schemes for modern power grids, systematically analyzing underlying technologies, key challenges, and emerging opportunities. A structured taxonomy of AI methodologies—ranging from Machine Learning (ML) and Deep Learning (DL) to Reinforcement Learning (RL) and hybrid systems—is developed, with a focus on their applications in fault detection, classification, location, and adaptive relay coordination. Particular emphasis is placed on recent advancements reported after 2022, highlighting the adoption of advanced models such as Vision Transformers, Graph Neural Networks (GNNs), and Physics-Informed Neural Networks (PINNs) to address grid nonlinearity and data scarcity. Furthermore, the paper critically examines major barriers to large-scale deployment, including explainability (XAI), cybersecurity vulnerabilities, and real-time computational constraints. Finally, a strategic roadmap is proposed, identifying future research directions such as digital twins, federated learning, and edge AI to bridge the gap between theoretical models and practical, self-healing protection systems.

Keywords

Main Subjects

References

Alhamrouni, I., Kahar, N. H. A., Salem, M., Swadi, M., Zahroui, Y., Kadhim, D. J., & Nazari, M. A. (2024). A comprehensive review on the role of artificial intelligence in power system stability, control, and protection. Appl. Sci., 14(14), 6214. https://doi.org/10.3390/app14146214.
Alsaiari, A., & Ilyas, M. (2025). A hybrid CNN-LSTM deep learning model for intrusion detection in smart grid. arXiv preprint. https://doi.org/10.48550/arXiv.2509.07208.
Aziz, M. Z. Yousaf, R. Fu, W. Khan, U. Siddique, M. Ahmad, & Zaitsev, I. (2025). Advanced AI-driven techniques for fault and transient analysis in high-voltage power systems. Sci. Rep., 15(1), 5592. https://doi.org/10.1038/s41598-025-90055-7.
Bakkar, M., Bogarra, S., Córcoles, F., Aboelhassan,V., Wang, S., & Iglesias. J. (2022). Artificial intelligence-based protection for smart grids. Energies, 15(13), 4933. https://doi.org/10.3390/en15134933.
Caldas, R. D., Rodrigues, A., Gil, E. B., Rodrigues, G. N., Vogel, T., & Pelliccione, P. (2020, Jun). A hybrid approach combining control theory and AI for self-adaptive systems. In Proc. IEEE/ACM SEAMS (pp. 9–19). https://doi.org/10.1145/3387939.3391595.
Chinnaraju, A.  (2025). Explainable AI (XAI) for trustworthy and transparent decision-making. World J. Adv. Eng. Technol. Sci., 14(3), 170–207. https://doi.org/10.30574/wjaets.2025.14.3.0106.
Choudhary, M., Vijitha, S., Bhavani, D. D., Bhuvaneswari, N., Tiwari, M., & Subburam, S. ( 2025). Edge AI: Deploying artificial intelligence models on edge devices. ITM Web Conf., 76, 01009. https://doi.org/10.1051/itmconf/20257601009
Dasand, S., & Panigrahi, B. K.  (2022). A PMU-based data-driven approach for enhancing situational awareness. IEEE Trans. Ind. Informat., 18(7), 4773–4784. https://doi.org/10.1109/TII.2022.3147794.
Diahovchenko, I., Kolcun, M., Čonka, Z., Savkiv, V., & Mykhailyshyn, R. ( 2020). Progress and challenges in smart grids. Iran. J. Sci. Technol. Trans. Electr. Eng., 44(4), 1319–1333. https://doi.org/10.1007/s40998-020-00322-8
Dinneweth, J., et al. (2022). Multi-agent reinforcement learning for autonomous vehicles: A survey. https://doi.org/10.1007/s43684-022-00045-z.
Grotto, A. J., & Dempsey, J. (2021). Vulnerability disclosure and management for AI/ML systems: A working paper with policy recommendations. ML Systems Working Paper. http://dx.doi.org/10.2139/ssrn.3964084
Hafez, S., Alkhedher, M., Ramadan, M., Gad, A., Alhalabi, M., Yaghi, M., & Ghazal, M. (2025). Advancements in grid resilience: Recent innovations in AI-driven solutions. Results Eng., 26, 105042. https://doi.org/10.1016/j.rineng.2025.105042.
He, J., & Zhao, H. (2020, December). Fault diagnosis and location based on graph neural network in telecom networks. In Proc. Int. Conf. Networking and Network Applications (NaNA) (pp. 304–309). https://doi.org/10.1109/NaNA51271.2020.00059.
Henao, F., Edgell, R., Sharma, A., & Olney, J. ( 2025). AI in power systems: A systematic review of key matters of concern. Energy Inform, 8(1), 76. https://doi.org/10.1186/s42162-025-00529-1.
Hijazi, M., et al. (2023). Transfer learning for transient stability predictions. IEEE Trans. Autom. Sci. Eng. https://doi.org/10.1109/TASE.2023.3277536.
Idrisov, N., et al. (2025). Leveraging digital twin and machine learning techniques for anomaly detection. https://doi.org/10.48550/arXiv.2501.13474.
Jamshidi Gahrouei, A., Falah, M., Azarbad, H., & Khorshidpour, S. (2026). Designing smart contract on a blockchain network for the purpose of trading energy from photovoltaic power plants. International Journal of Smart Electrical Engineering, 14(3), 171-178. https://doi.org/10.82234/IJSEE.2025.1208414.
Khaw, Y. M.,  Jahromi, A. A., Arani, M. F., Sanner, S., Kundur, D., & Kassouf, M.(2021). A deep learning-based cyberattack detection system. IEEE Trans. Smart Grid, 12(3), 2554–2565. https://doi.org/10.1109/TSG.2020.3040361.
Krause, T., et al. (2021). Cybersecurity in power grids. Sensors. https://doi.org/10.48550/arXiv.2105.00013
Livani, H., & Evrenosoglu, C. Y. (2013). A machine learning and wavelet-based fault location method. IEEE Trans. Smart Grid. https://doi.org/10.1109/TSG.2013.2260421.
Lotfifard, S., Faiz, J., & Kezunovic, M. (2009). Detection of symmetrical faults during power swings. IEEE Trans. Power Delivery,. https://doi.org/10.1109/TPWRD.2009.2035224.
Machlev, R., Heistrene, L., Perl, M., Levy, K. Y., Belikov, J., Mannor, S., & Levron, Y.(2022). Explainable artificial intelligence techniques for energy systems. Energy AI, 9, 100169. https://doi.org/10.1016/j.egyai.2022.100169.
Mazumder, M., Banbury, C., & Reddi, V. J. (2023). Data-centric AI benchmarks and evaluation. IEEE Micro, 43(2), 12–20, 2023. https://doi.org/10.48550/arXiv.2207.10062.
Mazumder, M., Banbury, C., Yao, X., Karlaš, B., Rojas, W. G., Diamos, S., & Reddi, V. J. (2023). Dataperf: Benchmarks for data-centric AI development. Adv. Neural Inf. Process. Syst., 36, 5320–5347. https://doi.org/10.48550/arXiv.2207.10062
Meloni, A., Pegoraro, P. A., Atzori, L., Benigni, A.,& Sulis, S. (2018). Cloud-based IoT solution for state estimation in smart grids. Comput. Netw., 130, 156–165. https://doi.org/10.1109/ICEPES60647.2024.10653566.
Meng, Q., Hussain, S., Luo, F., Wang, Z., & Jin, X. (2024). An online reinforcement learning-based energy management strategy for microgrids. IEEE Trans. Ind. Appl. https://doi.org/10.1016/j.est.2024.115114.
Mishra, M., & Singh, J. G. (2025). A comprehensive review on deep learning techniques in power system protection: Trends, challenges, applications and future directions. Results Eng., 103884. https://doi.org/10.1016/j.rineng.2025.107863.
Nadal, I. V., et al. (2025). Physics-informed neural networks in power system dynamics. https://doi.org/10.48550/arXiv.2501.17621.
Oelhaf, J., Kordowich, G., Pashaei, M., Bergler, C., Maier, A., Jäger, J., & Bayer, S. (2025). A scoping review of machine learning applications in power system protection and disturbance management. Int. J. Electr. Power Energy Syst., 172, 111257. https://doi.org/10.48550/arXiv.2509.09053.
Rizzato, M., et al. (2022). Stress testing electrical grids using GANs. Energy AI. https://doi.org/10.1016/j.egyai.2022.100177.
Sidhu, T. S., & Gangadharan, P. K. (2005). Control and automation of power system substation using IEC 61850. Proc. IEEE CCA, 1331–1336. https://doi.org/10.1109/CCA.2005.1507316.
Wen, M., Xie, R., Lu, K., Wang, L., & Zhang, K. (2021). FedDetect: A novel privacy-preserving federated learning framework for energy theft detection in smart grid. IEEE Internet Things J., 9(8), 6069–6080. https://doi.org/10.1109/JIOT.2021.3110784.
Zhang, J., et al. (2026). A characteristic oriented probabilistic stability assessment method based on PINN. https://doi.org/ 10.1016/j.ijepes.2025.111504.
Zhang, W., Yang, D., & Wang, H. (2019). Data-driven methods for predictive maintenance: A survey. IEEE Syst. J., 13(3), 2213–2227. https://doi.org/10.1109/JSYST.2019.2905565.
Journal of Data Analytics and Intelligent Decision-making
Volume 2, Issue 1 - Serial Number 4
January 2026
Pages 17-30

Files

Share

How to cite

Statistics