Real-Time EV Charger Load Balancing Using Reinforcement Learning Algorithms

Raj, Yaser

doi:10.25673/123753

Proceedings of International Conference on Applied Innovation in IT · 2026/03/31 · Vol. 14 · Issue 1 · pp. 1451–1458

Real-Time EV Charger Load Balancing Using Reinforcement Learning Algorithms

Yaser Issam Hamodi Aljanabi and Gaurav Raj

📄 Download PDF DOI: 10.25673/123753

Abstract

The growing use of electric vehicles (EVs) is putting a lot of stress on power distribution systems. This is mostly because of uncoordinated charging, which causes demand peaks, voltage fluctuations, and higher operating costs. This research introduces a reinforcement learning (RL)-based framework for real-time electric vehicle (EV) charger load balancing, aimed at concurrently optimizing grid stability, energy expenses, and user quality of service (QoS). The charging issue is framed as a Markov Decision Process, in which the RL agent distributes charging power based on feeder capacity, tariff signals, and state-of-charge (SoC) prerequisites. A safety layer makes sure that operational limits are followed. The proposed RL method cuts peak demand by up to 25% and energy costs by about 20%, while maintaining 95% QoS. This is much better than baseline scheduling methods. The framework also works well in stressful situations like arrival bursts, tariff changes, and feeder capacity cuts. These results show that RL is a good way to manage EV charging in real time that can be scaled up and is smart.

Keywords

Electric Vehicles Load Balancing Reinforcement Learning Peak Shaving Smart Charging Demand Response Real-Time Optimization.

References

Z. Wan, H. Li, H. He, and D. Prokhorov, “Model-free real-time EV charging scheduling based on deep reinforcement learning,” IEEE Transactions on Smart Grid, vol. 10, no. 5, pp. 5246-5257, 2018.
V. R. Chifu, T. Cioara, C. B. Pop, H. G. Rusu, and I. Anghel, “Deep Q-learning-based smart scheduling of EVs for demand response in smart grids,” Applied Sciences, vol. 14, no. 4, Art. no. 1421, 2024.
Y. Xia, Z. Cheng, J. Zhang, and X. Chen, “User cost minimization and load balancing for multiple electric vehicle charging stations based on deep reinforcement learning,” World Electric Vehicle Journal, vol. 16, no. 3, Art. no. 184, 2025.
I. Azzouz and W. Fekih Hassen, “Optimization of electric vehicles charging scheduling based on deep reinforcement learning: A decentralized approach,” Energies, vol. 16, no. 24, Art. no. 8102, 2023.
U. M. Damodarin, G. C. Cardarilli, L. Di Nunzio, M. Re, and S. Spanò, “Smart electric vehicle charging management using reinforcement learning on FPGA platforms,” Sensors, vol. 25, no. 8, Art. no. 2585, 2025.
J. Wang, L. Zhao, and Y. Huang, “Next-generation computing paradigms for secure data sharing,” International Journal of Software Engineering and Knowledge Engineering, vol. 35, no. 2, pp. 225-240, 2025, [Online]. Available: https://doi.org/10.1142/S0219649225500406.
V. Mehta and S. Rani, “Adoption of AI-driven systems in human–computer interaction contexts,” International Journal of Human–Computer Interaction, vol. 41, no. 6, pp. 701-718, 2025, [Online]. Available: https://doi.org/10.1080/10447318.2025.2480826.
L. T. Nguyen and M. Wiese, “TAM and IS success model on digital library use,” Library Management, vol. 24, no. 1-2, pp. 173-185, 2003, [Online]. Available: https://doi.org/10.1108/01435120310454592.
A. Poddubnyy, P. Nguyen, and H. Slootweg, “Online EV charging controlled by reinforcement learning with experience replay,” Sustainable Energy, Grids and Networks, vol. 36, Art. no. 101162, 2023.
S. Zhang, R. Jia, H. Pan, and Y. Cao, “A safe reinforcement learning-based charging strategy for electric vehicles in residential microgrid,” Applied Energy, vol. 348, Art. no. 121490, 2023.
S. Ghode and M. Digalwar, “Enhanced electric vehicle charging strategy through graph convolutional networks integrated with deep reinforcement learning,” International Journal of Information Technology, pp. 1-13, 2025.
M. Saklani, D. K. Saini, M. Yadav, and P. Siano, “Scalable data-driven EV charging optimization using HDBSCAN-LP for real-time pricing load management,” Smart Cities, vol. 8, no. 4, 2025.
N. Brinkel, T. van Wijk, A. Buijze, N. K. Panda, J. Meersmans, P. Markotić, and W. van Sark, “Enhancing smart charging in electric vehicles by addressing paused and delayed charging problems,” Nature Communications, vol. 15, no. 1, Art. no. 5089, 2024.
J. A. Guerrero-Silva, J. I. Romero-Gelvez, A. J. Aristizábal, and S. Zapata, “Optimization and trends in EV charging infrastructure: A PCA-based systematic review,” World Electric Vehicle Journal, vol. 16, no. 7, Art. no. 345, 2025.
A. S. Lateef and A. A. L. Hawar, “Using artificial intelligence techniques in advertising production,” Iraqi Journal of Applied Art, vol. 1, no. 2, pp. 10-15, 2025, [Online]. Available: https://doi.org/10.51173/ijaa.v1i2.56.
H. M. Saad and M. J. Mhawes, “The relationship and impact of the external auditor’s fees on audit quality of financial statements: A case study on audit companies and offices operating in Iraq,” Technical Journal of Management Sciences, vol. 2, no. 1, pp. 41-53, 2025, [Online]. Available: https://doi.org/10.51173/tjms.v2i1.25.