A bio-inspired neuromorphic framework for decentralized fault detection and renewable optimization in smart grids

Mohammad Barr; Tawfeeq Shawly; Ahmed A. Alsheikhy; Yahia Said; Shaaban M. Shaaban; Aws AbuEid; Mohammad Barr; Tawfeeq Shawly; Ahmed A. Alsheikhy; Yahia Said; Shaaban M. Shaaban; Aws AbuEid

doi:10.3934/math.2026627

AIMS Mathematics

2026, Volume 11, Issue 5: 15233-15276. doi: 10.3934/math.2026627

Previous Article Next Article

Research article

A bio-inspired neuromorphic framework for decentralized fault detection and renewable optimization in smart grids

1.
Department of Electrical Engineering, College of Engineering, Northern Border University, Arar 91431, Saudi Arabia; mohammed.barr@nbu.edu.sa
2.
Department of Electrical Engineering, Faculty of Engineering at Rabigh, King Abdulaziz University, Jeddah 21589, Saudi Arabia; tshawly@kau.edu.sa
3.
Department of Computer and Network Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 21959, Saudi Arabia; aaalsheikhy@uj.edu.sa
4.
Center for Scientific Research and Entrepreneurship, Northern Border University, Arar 73213, Saudi Arabia; Yahia.said@nbu.edu.sa, shaban.awdallah@nbu.edu.sa
5.
Department of Information and Communication Technology, College of Computing Studies, Arab Open University, Kuwait Branch, Kuwait; a.abueid@arabou.edu.kw

Received: 28 January 2026 Revised: 13 April 2026 Accepted: 16 April 2026 Published: 29 May 2026
MSC : 68T07, 68T10, 68T20

Modern smart grids encounter several challenges, including the variability of renewable energy sources with power fluctuations of ±35% in solar farms across the Arabian Gulf countries, delays in centralized control, with latencies of 150–200 ms, including all time needed from sending data to receiving control commands, and increased susceptibility to cyber threats, with a 30% annual increase in grid intrusions. Incorporating renewable energy into smart grids presents significant challenges, including intermittent generation, characterized by ±30% solar volatility, slow fault detection, and response times exceeding 500 ms in traditional systems, as well as centralized system weaknesses. This paper presents SwarmNet-5G, a bio-inspired neural network that integrates stigmergic learning and spiking neural networks (SNNs) for decentralized grid management to resolve existing issues. It merges Internet of Things (IoT)-edge intelligence, spiking neuromorphic computing, and swarm-based stigmergy to enable grid optimization. Its design decreases latency by 40% compared to typical deep reinforcement learning (DRL). It achieves a fault detection accuracy of 99.62% within 8.17 ms and requires 50 ms for repair, aligning with Saudi Arabia's Vision 2030 goal of achieving 50% renewable energy. Simulation results performed on the IEEE 39-bus using a dataset show that the solution allocated power during peak demand, such as a 20% load increase, with an efficiency of 92%, while typical DRL reached 78%. Additionally, the model projected annual savings of.2B in maintenance costs and a reduction of 4.8 megatons in CO₂ emissions per year.
- decentralized neuromorphic computing,
- 5G-IoT smart grids,
- stigmergic energy optimization,
- self-healing microgrids,
- spiking neural networks
Citation: Mohammad Barr, Tawfeeq Shawly, Ahmed A. Alsheikhy, Yahia Said, Shaaban M. Shaaban, Aws AbuEid. A bio-inspired neuromorphic framework for decentralized fault detection and renewable optimization in smart grids[J]. AIMS Mathematics, 2026, 11(5): 15233-15276. doi: 10.3934/math.2026627

Related Papers:

Abstract

Modern smart grids encounter several challenges, including the variability of renewable energy sources with power fluctuations of ±35% in solar farms across the Arabian Gulf countries, delays in centralized control, with latencies of 150–200 ms, including all time needed from sending data to receiving control commands, and increased susceptibility to cyber threats, with a 30% annual increase in grid intrusions. Incorporating renewable energy into smart grids presents significant challenges, including intermittent generation, characterized by ±30% solar volatility, slow fault detection, and response times exceeding 500 ms in traditional systems, as well as centralized system weaknesses. This paper presents SwarmNet-5G, a bio-inspired neural network that integrates stigmergic learning and spiking neural networks (SNNs) for decentralized grid management to resolve existing issues. It merges Internet of Things (IoT)-edge intelligence, spiking neuromorphic computing, and swarm-based stigmergy to enable grid optimization. Its design decreases latency by 40% compared to typical deep reinforcement learning (DRL). It achieves a fault detection accuracy of 99.62% within 8.17 ms and requires 50 ms for repair, aligning with Saudi Arabia's Vision 2030 goal of achieving 50% renewable energy. Simulation results performed on the IEEE 39-bus using a dataset show that the solution allocated power during peak demand, such as a 20% load increase, with an efficiency of 92%, while typical DRL reached 78%. Additionally, the model projected annual savings of.2B in maintenance costs and a reduction of 4.8 megatons in CO₂ emissions per year.

References

[1]	X. Fang, S. Misra, G. Xue, D. Yang, Smart grid—The new and improved power grid: A Survey, IEEE Commun. Surv. Tutor., 14 (2012), 944–980. https://doi.org/10.1109/SURV.2011.101911.00087 doi: 10.1109/SURV.2011.101911.00087
[2]	V. C. Gungor, D. Sahin, T. Kocak, S. Ergut, C. Buccella, C. Cecati, et al., A survey on smart grid potential applications and communication requirements, IEEE Trans. Industr. Inform., 9 (2013), 28–42. https://doi.org/10.1109/TII.2012.2218253 doi: 10.1109/TII.2012.2218253
[3]	P. Palensky, D. Dietrich, Demand side management: Demand response, intelligent energy systems, and smart loads, IEEE Trans. Industr. Inform., 7 (2011), 381–388. https://doi.org/10.1109/TII.2011.2158841 doi: 10.1109/TII.2011.2158841
[4]	H. Farhangi, The path of the smart grid, IEEE Power Energy Mag., 8 (2010), 18–28. https://doi.org/10.1109/MPE.2009.934876 doi: 10.1109/MPE.2009.934876
[5]	M. B. Mollah, J. Zhao, D. Niyato, K. Y. Lam, X. Zhang, A. M. Y. M. Ghias, et al., Blockchain for future smart grid: A comprehensive survey, IEEE Internet Things J., 8 (2021), 18–43. https://doi.org/10.1109/JIOT.2020.2993601 doi: 10.1109/JIOT.2020.2993601
[6]	X. J. Li, M. Ma, Y. Sun, An adaptive deep learning neural network model to enhance machine-learning-based classifiers for intrusion detection in smart grids, Algorithms, 16 (2023), 288. https://doi.org/10.3390/a16060288 doi: 10.3390/a16060288
[7]	S. Stavrev, D. Ginchev, Reinforcement learning techniques in optimizing energy systems, Electronics, 13 (2024), 1459. https://doi.org/10.3390/electronics13081459 doi: 10.3390/electronics13081459
[8]	D. Latoń, J. Grela, A. Ożadowicz, Applications of deep reinforcement learning for home energy management systems: A review, Energies, 17 (2024), 6420. https://doi.org/10.3390/en17246420 doi: 10.3390/en17246420
[9]	B. L. H. Nguyen, T. V. Vu, T. Nguyen, M. Panwar, R. Hovsapian, Spatial-temporal recurrent graph neural networks for fault diagnostics in power distribution systems, IEEE Access, 11 (2023), 46039–46050. https://doi.org/10.1109/ACCESS.2023.3273292 doi: 10.1109/ACCESS.2023.3273292
[10]	Y. Zhong, T. Li, K. Przystupa, C. Lin, G. Yang, S. Yang, et al., Spatiotemporal correlation analysis for predicting current transformer errors in smart grids, Energies, 17 (2024), 1608. https://doi.org/10.3390/en17071608 doi: 10.3390/en17071608
[11]	N. W. Branco, M. S. M. Cavalca, S. F. Stefenon, V. R. Q. Leithardt, Wavelet LSTM for fault forecasting in electrical power grids, Sensors, 22 (2022), 8323. https://doi.org/10.3390/s22218323 doi: 10.3390/s22218323
[12]	IEA, Tracking clean energy progress 2023. Available from: https://www.iea.org/reports/tracking-clean-energy-progress-2023
[13]	J. Jithish, B. Alangot, N. Mahalingam, K. S. Yeo, Distributed anomaly detection in smart grids: A federated learning-based approach, IEEE Access, 11 (2023), 7157–7179. https://doi.org/10.1109/ACCESS.2023.3237554 doi: 10.1109/ACCESS.2023.3237554
[14]	J. Qiu, X. Zhang, T. Wang, H. Hou, S. Wang, T. Yang, A GNN-based false data detection scheme for smart grids, Algorithms, 18 (2025), 166. https://doi.org/10.3390/a18030166 doi: 10.3390/a18030166
[15]	Q. Shuai, Y. Yin, S. Huang, C. Chen, Deep reinforcement learning-based real-time energy management for an integrated electric–thermal energy system, Sustainability, 17 (2025), 407. https://doi.org/10.3390/su17020407 doi: 10.3390/su17020407
[16]	R. Qi, C. Rasband, J. Zheng, R. Longoria, Detecting cyber attacks in smart grids using semi-supervised anomaly detection and deep representation learning, Information, 12 (2021), 328. https://doi.org/10.3390/info12080328 doi: 10.3390/info12080328
[17]	B. Khan, Z. Ullah, G. Gruosso, Enhancing grid stability through physics-informed machine learning integrated-model predictive control for electric vehicle disturbance management, World Electr. Veh. J., 16 (2025), 292. https://doi.org/10.3390/wevj16060292 doi: 10.3390/wevj16060292
[18]	B. Vivek, B. H. Teja, B. Mallala, G. Srinitha, Electrical fault detection and localization using machine learning, In: 2024 International conference on expert clouds and applications (ICOECA), India: IEEE, 2024,820–825. https://doi.org/10.1109/ICOECA62351.2024.00145
[19]	V. K. Paravasthu, B. Mallala, B. Mangu, S. R. Salkuti, Optimizing renewable energy integration and electric vehicle charging stations in distribution networks using hybrid whale optimization algorithm, In: Artificial intelligence for integrated smart energy systems in electric vehicles, Cham: Springer, 1427 (2025), 105–144. https://doi.org/10.1007/978-3-031-94276-1_6
[20]	B. Mallala, A. I. U. Ahmed, S. V. Pamidi, O. Faruque, R. M. Reddy, Forecasting global sustainable energy from renewable sources using random forest algorithm, Results Eng., 25 (2025), 103789. https://doi.org/10.1016/j.rineng.2024.103789 doi: 10.1016/j.rineng.2024.103789
[21]	K. Quizhpe, P. Arévalo, D. Ochoa-Correa, E. Villa-Ávila, Optimizing microgrid planning for renewable integration in power systems: A comprehensive review, Electronics, 13 (2024), 3620. https://doi.org/10.3390/electronics13183620 doi: 10.3390/electronics13183620
[22]	M. Davies, N. Srinivasa, T. H. Lin, G. Chinya, Y. Q. Cao, S. H. Choday, et al., Loihi: A neuromorphic manycore processor with On-Chip learning, IEEE Micro, 38 (2018), 82–99. https://doi.org/10.1109/MM.2018.112130359 doi: 10.1109/MM.2018.112130359

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)