Abstract

This research introduces EvoGridNet, a novel self-healing framework for electrical power grids using Evolutionary Graph Neural Networks (EGNNs) to dynamically reconfigure topologies post cyber-physical attacks. By embedding domain-specific modules including Ant Colony Optimization (ACO), Bidirectional LSTM, Soft Actor-Critic (SAC), and Siamese Networks, this model autonomously recovers grid stability across Earth-based, aerial, and space missions. The algorithm integrates energy trading via smart contracts and enforces cyber resilience using residual deep learning and weather-aware reactivity. Experimental implementation in Python (Colab) confirms enhanced fault recovery, reduced outage durations, and autonomous topology reformation.

Downloads

Download data is not yet available.

References

  1. [1] M. Liu, H. Li, Y. Chen, and Q. Zhu, “Resilient Grid Optimization under Cyber Threats,” IEEE Transactions on Smart Grid, vol. 12, no. 1, pp. 741–752, Jan. 2021. [Online]. Available: https://doi.org/10.1109/TSG.2020.2994812
  2. [2] Y. Zhang, X. Wang, J. Li, and M. Tao, “Graph Neural Networks for Power Grid Topology Inference,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 5, pp. 2084–2096, May 2022. [Online]. Available: https://doi.org/10.1109/TNNLS.2021.3065845
  3. [3] L. Wang and B. Chen, “Adaptive Grid Restructuring Algorithms for Power System Stability,” IEEE Access, vol. 8, pp. 135321–135333, Jul. 2020. [Online]. Available: https://doi.org/10.1109/ACCESS.2020.3010463
  4. [4] A. Jain and S. Bose, “Ant Colony Optimization for Peak Load Reduction in Smart Grids,” IEEE Transactions on Smart Grid, vol. 13, no. 2, pp. 1051–1061, Mar. 2022. [Online]. Available: https://doi.org/10.1109/TSG.2021.3112054
  5. [5] R. Hameed, M. Asad, and L. Wei, “Voltage and VAR Control Using Bidirectional LSTM Networks,” IEEE Transactions on Power Delivery, vol. 36, no. 3, pp. 1541–1550, Jun. 2021. [Online]. Available: https://doi.org/10.1109/TPWRD.2020.3044781
  6. [6] F. Zhang, H. Xu, and Y. Deng, “Satellite Energy Management Using Soft Actor-Critic Deep Reinforcement Learning,” IEEE Transactions on Aerospace and Electronic Systems, vol. 58, no. 1, pp. 380–390, Feb. 2022. [Online]. Available: https://doi.org/10.1109/TAES.2021.3059942
  7. [7] T. Kwon and M. R. Asif, “Predicting Insulation Aging in Electric Grids Using Residual Neural Networks,” IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp. 2638–2647, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TII.2020.3014875
  8. [8] S. Javed and K. Niazi, “Topology Change Detection in Smart Grids Using Siamese Neural Networks,” IEEE Transactions on Power Systems, vol. 37, no. 2, pp. 1445–1454, Mar. 2022. [Online]. Available: https://doi.org/10.1109/TPWRS.2021.3097614.
 How to Cite
[1]
Zaidi, A.H. 2025. EvoGridNet: Post-Attack Self-Healing Electric Grids via Evolutionary Graph Neural Topologies and AI-Driven Reconfiguration. International Journal of Science and Engineering Invention. 11, 06 (Jul. 2025), 89–95. DOI:https://doi.org/10.23958/ijsei/vol11-i06/292.

Copyrights & License