Citation :

Vadivel S, Prakash M, "Topology-Aware Federated Multi-Agent Reinforcement Learning for Dual-Level Voltage Regulation in PV-Rich Distribution Grids," International Journal of Electrical and Electronics Engineering, vol. 13, no. 10, pp. 49-61, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I10P105

Abstract

Photovoltaic (PV) generation with high penetration in the distribution networks causes voltage rise, voltage deviation and three-phase imbalance between connected Medium-Voltage (MV) and Low-Voltage (LV) feeders. In this paper, a topology-conscious federated multi-agent reinforcement learning is introduced to subordinated dual-level voltage regulation in PV-rich distribution grids. The given approach represents the network as a graph and implements the state encoding with the help of a Graph Neural Network (GNN) to ensure that every agent is able to represent local electrical state and local topology. Both LV control nodes are considered independent reinforcement learning agents, and the federated aggregation provides the means of updating shared parameters of the model without sharing the raw local measurements. The structure is aimed at minimizing MV voltage violations and LV phase unbalance collaboratively when there are different conditions of PV penetration and communication. The technique is tested on a stochastic load and PV test system on the IEEE 33-bus distribution test system. The findings show that voltage regulation and phase-balancing performance are enhanced when using the centralized RL strategy instead of baseline centralized RL and traditional MARL strategies. The research identifies the promise of topology-conscious learning and federated coordination in the provision of scalable voltage control in privacy-sensitive smart grid systems.

Keywords

Federated learning, Reinforcement learning, Graph Neural Networks, Voltage regulation, PV integration, Smart grids, Multi-Agent systems.

References

1. Daner Hu et al., “Multi-Agent Deep Reinforcement Learning for Voltage Control with Coordinated Active and Reactive Power Optimization,” IEEE Transactions on Smart Grid, vol. 13, no. 6, pp. 4873-4886, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Mengfan Zhang et al., “Multi-Agent Deep Reinforcement Learning for Decentralized Voltage-Var Control in Distribution Power System,” 2022 IEEE Energy Conversion Congress and Exposition (ECCE), Detroit, MI, USA, pp. 1-5, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Di Cao et al., “Deep Reinforcement Learning Enabled Physical-Model-Free Two-Timescale Voltage Control Method for Active Distribution Systems,” IEEE Transactions on Smart Grid, vol. 13, no. 1, pp. 149-165, 2021.
   [CrossRef] [Google Scholar] [Publisher Link] 
4. Bin Zhang et al., “Physics-Informed Multi-Agent Deep Reinforcement Learning Enabled Distributed Voltage Control for Active Distribution Network using PV Inverters,” International Journal of Electrical Power and Energy Systems, vol. 155, pp. 1-15, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]  
5. Canbing Li et al., “Fault Mitigation Mechanism to Pave the Way to Accommodate Over 90% Renewable Energy in Electric Power Systems,” Applied Energy, vol. 359, pp. 1-9, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]   
6. Sayak Mukherjee et al., “Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations,” IEEE Transactions on Smart Grid, vol. 16, no. 2, pp. 1897-1910, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]    
7. Mengfan Zhang, and Qianwen Xu, Safe Deep Reinforcement Learning for Renewable Energy Integrated Power System,” Digitalisation of Local Energy Systems, Springer, Cham, pp. 313-336, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]    
8. P. Joshua Reginald, “Hybrid AC/DC Microgrid Power Management using Intelligent Power Electronics Interfaces,” Transactions on Power Electronics and Renewable Energy Systems, vol. 1, no. 1, pp. 21-29, 2025.
   [Google Scholar] [Publisher Link]    
9. Madhanraj, “AI-Powered Energy Forecasting Models for Smart Grid-Integrated Solar and Wind Systems,” National Journal of Renewable Energy Systems and Innovation, vol. 1, no. 1, pp. 1-7, 2025.
   [Publisher Link]  
10. J. Jithish et al., “Distributed Anomaly Detection in Smart Grids: A Federated Learning-based Approach,” IEEE Access, vol. 11, pp. 7157-7179, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]  
11. Islam M. Saad et al., “Smart Grid Prediction using Federated Learning and Fully Homomorphic Encryption,” 2024 34^th International Conference on Computer Theory and Applications (ICCTA), Alexandria, Egypt, pp. 335-342, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]   
12. Prerna Dusi, “AI-Augmented Runtime Reconfigurable Hardware Architectures for Energy-Efficient Edge Intelligence,” Journal of Reconfigurable Hardware Architectures and Embedded Systems, vol. 3, no. 1, pp. 10-17, 2025.
    [Google Scholar] [Publisher Link]     
13. Ms Annette Nellyet, “Chaos-Sensitive Encryption Frameworks based on Hyper Chaotic Circuit Topologies for Secure Communication,” Applied Nonlinearity in Science and Technology, vol. 1, no. 1, pp. 25-29, 2025.
    [Google Scholar] [Publisher Link]
14. T. Vishnupriya, “A Federated Learning Framework for Privacy-Preserving Energy Forecasting in IoT-Enabled Smart Grids,” National Journal of Intelligent Power Systems and Technology, vol. 1, no. 1, pp. 38-47, 2025.
    [Google Scholar] [Publisher Link]     
15. Haotian Liu, and Wenchuan Wu, “Federated Reinforcement Learning for Decentralized Voltage Control in Distribution Networks,” IEEE Transactions on Smart Grid, vol. 13, no. 5, pp. 3840-3843, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]    
16. Wenlong Liao et al., “A Review of Graph Neural Networks and their Applications in Power Systems,” Journal of Modern Power Systems and Clean Energy, vol. 10, no. 2, pp. 345-360, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Koji Yamashita et al., “Predicting Power System Voltage Health Index with PMUs and Graph Convolutional Networks,” 2023 IEEE Power and Energy Society General Meeting (PESGM), Orlando, FL, USA, pp. 1-5, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. T. Vishnupriya, “Grid-Connected Inverter Topologies for High-Penetration Solar PV Systems: A Comparative Study,” Transactions on Power Electronics and Renewable Energy Systems, vol. 1, no. 1, pp. 44-50, 2025.
    [Google Scholar] [Publisher Link]  
19. Sangwoo Park et al., “Distributed Power System State Estimation using Graph Convolutional Neural Networks,” Proceedings of the 56^th Hawaii International Conference on System Sciences, pp. 2756-2765, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
20. S.N. Ayrapetyan, and Barek F. Fatem, “Intelligent Hybrid Renewable–Energy Storage Systems for Resilient and Sustainable Power Networks,” National Journal of Electrical Electronics and Automation Technologies, vol. 1, no. 3, pp. 27-34, 2025.
    [Google Scholar] [Publisher Link]
21. K.P. Uvarajan, and Rajan. C, “Model Predictive Control-based Bidirectional EV Charging Strategy for Grid Load Shaping and Cost Optimization in Smart Grids,” Electronics Communications, and Computing Summit, vol. 2, no. 4, pp. 86-91, 2024.
    [Google Scholar] [Publisher Link]
22. Jiapeng Huang et al., “Multi-Agent Deep Reinforcement Learning with Enhanced Collaboration for Distribution Network Voltage Control,” Engineering Applications of Artificial Intelligence, vol. 134, pp. 1-12, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Chenyi Zhuang, and Qiang Ma, “Dual Graph Convolutional Networks for Graph-based Semi-Supervised Classification,” Proceedings of the 2018 World Wide Web Conference, International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, pp. 499-508, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
24. A. Velliangiri, “Context-Aware Digital-Twin-Driven Learning Frameworks for Safe and Adaptive Energy Coordination in Intelligent Vehicular Environments,” Archives of Electronics, Communication and Emerging Technologies, vol. 1, no. 1, pp. 33-40, 2026.
    [Google Scholar] [Publisher Link]