RAME Logo

RAME PUBLISHERS

A better space for Quality Research
International Journal of Computational and Electronics Aspects in Engineering (IJCEAE)
Volume 7 · Issue 5 · November 2026 · pp. 659–672
Research Article · Peer Reviewed
Received: August 30, 2026 · Accepted: October 27, 2026 · Published: November 10, 2026
DOI: 10.26706/ijceae.7.5.20261010
Open Access · CC BY 4.0

Outage-Aware Smart Charging of Electric Vehicles in Weak Distribution Grids: Reinforcement Learning versus Model-Predictive Control

Mohammed Tariq Majeed*
Department of Medical Instrumentation Techniques Engineering, Polytechnic College Mosul, Northern Technical University, Mosul, Iraq.
ORCID: 0000-0001-6885-8597
*Correspondence: aldabgh68@ntu.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 5

Abstract

Charging electric vehicles in weak distribution grids with rationed electricity supply requires a controller that respects voltage and transformer limits, anticipates supply interruptions and decides when to use costly backup generation. This study compared reinforcement learning with model-predictive control for this task. A car park with 24 chargers at the end of a rural low-voltage benchmark feeder was simulated with 9148 real charging sessions and household load profiles, under rotating outage schedules of 20, 16 and 12 hours of daily supply that included schedule deviations and unscheduled interruptions.

Uncontrolled charging, least-laxity-first rules with and without outage awareness, rolling-horizon model-predictive control, three proximal-policy-optimisation agents and a perfect-information benchmark were evaluated on 122 held-out days, and all schedules were checked with alternating-current power flow. Uncontrolled charging violated the 0.90 per-unit voltage limit in 6.4% of charging intervals and overloaded the transformer by up to 35%, whereas all controlled strategies remained within the limits. Outage awareness reduced the unmet energy by 4–22%, and the reduction grew with outage severity. A simple outage-aware least-laxity rule matched model-predictive control to within 0.2% in daily cost. The learning agents lowered the daily cost by 1–5% by rationing generator energy more cautiously, but their advantage varied between training seeds, vanished when schedule information was missing and reversed when true departure times were available. Departure-time uncertainty, rather than outage uncertainty, explained 87% of the cost gap to perfect information.

Keywords

electric vehicle smart charging reinforcement learning model-predictive control power outages load shedding weak distribution grid voltage constraints backup generator

References

  1. S. Powell, G. Vianna Cezar, L. Min, I. M. L. Azevedo, and R. Rajagopal, “Charging infrastructure access and operation to reduce the grid impacts of deep electric vehicle adoption,” Nature Energy, vol. 7, no. 10, pp. 932–945, 2022, doi: 10.1038/s41560-022-01105-7.
  2. S. Ghanbari Motlagh, J. Oladigbolu, and L. Li, “A review on electric vehicle charging station operation considering market dynamics and grid interaction,” Applied Energy, vol. 392, Art. no. 126058, 2025, doi: 10.1016/j.apenergy.2025.126058.
  3. D. Qiu, Y. Wang, W. Hua, and G. Strbac, “Reinforcement learning for electric vehicle applications in power systems: A critical review,” Renewable and Sustainable Energy Reviews, vol. 173, Art. no. 113052, 2023, doi: 10.1016/j.rser.2022.113052.
  4. H. A. Mutar, I. J. Mohammed, and I. R. N. ALRubeei, “AI for solar PV forecasting, MPPT, and energy management: A comprehensive review,” International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 1, pp. 100–114, 2026, doi: 10.26706/ijceae.7.1.20260111.
  5. A. A. Hadi, “The impact of artificial neural network (ANN) on the solar energy cells: A review,” International Journal of Computational and Electronic Aspects in Engineering, vol. 5, no. 1, pp. 30–41, 2024, doi: 10.26706/ijceae.5.1.20240505.
  6. A. Al-Wakeel, “Local energy systems in Iraq: Neighbourhood diesel generators and solar photovoltaic generation,” in Microgrids and Local Energy Systems, N. Jenkins, Ed. London, U.K.: IntechOpen, 2021, doi: 10.5772/intechopen.95280.
  7. Z. Ali and H. Athari, “Beyond barrels and generators: Solar power economics and market potential in Iraq,” NTU Journal of Renewable Energy, vol. 10, no. 1, pp. 31–38, 2026, doi: 10.56286/nkp6b206.
  8. M. Wiese and L.-M. van der Westhuizen, “Impact of planned power outages (load shedding) on consumers in developing countries: Evidence from South Africa,” Energy Policy, vol. 187, Art. no. 114033, 2024, doi: 10.1016/j.enpol.2024.114033.
  9. G. Yu, X. Ye, and X. Xia, “Optimal parking lot retrofit planning for electric vehicle charging station during prolonged load shedding,” Energy, vol. 322, Art. no. 135624, 2025, doi: 10.1016/j.energy.2025.135624.
  10. J. Einolander, A. Kiviaho, and R. Lahdelma, “Valuing the household power outage self-sustainment capabilities of bidirectional electric vehicle charging,” Applied Energy, vol. 374, Art. no. 124071, 2024, doi: 10.1016/j.apenergy.2024.124071.
  11. M. Kadhim, “Improving power quality with active filtering and energy storage technologies in grid-connected hybrid solar-wind renewable energy systems,” International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 2, pp. 291–304, 2026, doi: 10.26706/ijceae.7.2.20260317.
  12. A. Di Giorgio, E. De Santis, L. Frettoni, S. Felli, and F. Liberati, “Electric vehicle fast charging: A congestion-dependent stochastic model predictive control under uncertain reference,” Energies, vol. 16, no. 3, Art. no. 1348, 2023, doi: 10.3390/en16031348.
  13. B. Kandpal, P. Pareek, and A. Verma, “A robust day-ahead scheduling strategy for EV charging stations in unbalanced distribution grid,” Energy, vol. 249, Art. no. 123737, 2022, doi: 10.1016/j.energy.2022.123737.
  14. Y. Li, Z. Zhang, and Q. Xing, “Real-time online charging control of electric vehicle charging station based on a multi-agent deep reinforcement learning,” Energy, vol. 319, Art. no. 135095, 2025, doi: 10.1016/j.energy.2025.135095.
  15. S. H. Mansour, S. M. Azzam, H. M. Hasanien, M. Tostado-Véliz, A. Alkuhayli, and F. Jurado, “Deep reinforcement learning-based plug-in electric vehicle charging/discharging scheduling in a home energy management system,” Energy, vol. 316, Art. no. 134420, 2025, doi: 10.1016/j.energy.2025.134420.
  16. 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, doi: 10.1016/j.apenergy.2023.121490.
  17. D. Liu, P. Zeng, S. Cui, and C. Song, “Deep reinforcement learning for charging scheduling of electric vehicles considering distribution network voltage stability,” Sensors, vol. 23, no. 3, Art. no. 1618, 2023, doi: 10.3390/s23031618.
  18. J. Arroyo, C. Manna, F. Spiessens, and L. Helsen, “Reinforced model predictive control (RL-MPC) for building energy management,” Applied Energy, vol. 309, Art. no. 118346, 2022, doi: 10.1016/j.apenergy.2021.118346.
  19. Z. J. Lee, T. Li, and S. H. Low, “ACN-Data: Analysis and applications of an open EV charging dataset,” in Proc. 10th ACM Int. Conf. Future Energy Systems (e-Energy ’19), 2019, pp. 139–149, doi: 10.1145/3307772.3328313.
  20. S. Meinecke, D. Sarajlić, S. R. Drauz, et al., “SimBench—A benchmark dataset of electric power systems to compare innovative solutions based on power flow analysis,” Energies, vol. 13, no. 12, Art. no. 3290, 2020, doi: 10.3390/en13123290.
  21. N. Chen, C. Kurniawan, Y. Nakahira, L. Chen, and S. H. Low, “Smoothed least-laxity-first algorithm for electric vehicle charging: Online decision and performance analysis with resource augmentation,” IEEE Transactions on Smart Grid, vol. 13, no. 3, pp. 2209–2217, 2022, doi: 10.1109/TSG.2021.3138615.
  22. L. Thurner, A. Scheidler, F. Schäfer, et al., “pandapower—An open-source Python tool for convenient modeling, analysis, and optimization of electric power systems,” IEEE Transactions on Power Systems, vol. 33, no. 6, pp. 6510–6521, 2018, doi: 10.1109/TPWRS.2018.2829021.
  23. CENELEC, Voltage Characteristics of Electricity Supplied by Public Electricity Networks, EN 50160, European Committee for Electrotechnical Standardization, Brussels, Belgium, 2010.
  24. Q. Huangfu and J. A. J. Hall, “Parallelizing the dual revised simplex method,” Mathematical Programming Computation, vol. 10, no. 1, pp. 119–142, 2018, doi: 10.1007/s12532-017-0130-5.
  25. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017, doi: 10.48550/arXiv.1707.06347.
  26. A. Raffin, A. Hill, A. Gleave, A. Kanervisto, M. Ernestus, and N. Dormann, “Stable-Baselines3: Reliable reinforcement learning implementations,” Journal of Machine Learning Research, vol. 22, no. 268, pp. 1–8, 2021. [Online]. Available: https://jmlr.org/papers/v22/20-1364.html.
  27. O. A. Abdaumran, “IoT-enabled real-time fault monitoring in overhead power lines using ESP32 and Arduino integrated development,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 3, pp. 190–201, 2025, doi: 10.26706/ijceae.6.3.20250610.
  28. I. A. Ameen and M. A. Al-Sheikh, “Wireless sensor networks for smart gardening: ESP-NOW and Blynk IoT integration for water and energy optimization,” International Journal of Computational and Electronic Aspects in Engineering, vol. 5, no. 3, pp. 101–115, 2024, doi: 10.26706/ijceae.5.3.20240804.
  29. S. Waghe, U. Kuradkar, S. Prajapati, and R. Mohane, “Detecting and reducing phantom power: A human-centric IoT approach,” International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 3, pp. 76–83, 2026, doi: 10.26706/ijceae.7.3.20260711.
  30. A. W. Talab, “Improving communication protocols based on crucial data transmission security for IoT techniques,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 1, pp. 1–11, 2025, doi: 10.26706/ijceae.6.1.20250203.
  31. S. Q. Ameen, R. G. S. Alsulta, Z. S. Hussain, and Z. T. Abdul-Rahmman, “A hybrid RSA–ElGamal framework for secure end-to-end communications in resource-constrained IoT networks,” International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 2, pp. 140–153, 2026, doi: 10.26706/ijceae.7.2.20260303.