Volume 6 , Issue 1 , PP: 33–42, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Heba Moselhy 1 * , Noura Metawa 2
Doi: https://doi.org/10.54216/JSDGT.060104
The efficient functioning of the electric-vehicle charging systems that are publicly operated has become focused on reliable short-horizon forecasting. The paper establishes an explainable and price-conscious analytical model to predict short-term charging usage and demonstrate the utility of tariff signals in an urban charging system. The analysis is based on UrbanEV benchmark, a new six months hourly panel of Shenzhen public charging infrastructure, which integrates occupancy, charging time, charging volume, electricity tariffs, service charges, weather and spatial descriptors. The concept of charging occupancy is considered an operation state variable with connection to queue exposure, reliability of service, and tactical intervention. A succinct mathematical formulation is created to use it in one-step-ahead utilization forecasting and in interpreting low-, medium-, and high-utilization regime. The empirical analysis is pegged to benchmark evidence reported to UrbanEV, where transformer-based forecasting had the best node-level performance and TimeXer had the best RMSE values of 0.07 in occupancy, 2.73 in charging duration, and 43.66 in charging volume. Further discussion indicates that occupancy prediction is accurate enough to justify regime based intervention and strongest additional gains are obtained through the joint effect of pricing variables and temperature-price interactions as opposed to single covariates. The results justify the justifiable, price-conscious forecasting as an operational decision tool to alleviate congestion, design tariffs and specific capacity planning in sustainable charging networks.
Electric vehicle charging , Utilization forecasting , Sustainable mobility , Dynamic pricing , Explainable analytics , Charging operations
[1] Tran, M., Banister, D., Bishop, J. D. K., and McCulloch, M. D. (2012). Realizing the electric-vehicle revolution. Nature Climate Change, 2(5), 328–333.
[2] Crabtree, G. (2019). The coming electric vehicle transformation. Science, 366(6464), 422–424.
[3] International Energy Agency. (2024). Global EV Outlook 2024. Paris: International Energy Agency.
[4] Muratori, M. (2018). Impact of uncoordinated plug-in electric vehicle charging on residential power demand. Nature Energy, 3(3), 193–201.
[5] Lee, Z. J., Li, T., and Low, S. H. (2019). ACN-Data: Analysis and Applications of an Open EV Charging Dataset. In Proceedings of the Tenth ACM International Conference on Future Energy Systems, 139–149.
[6] Aveklouris, A., Vlasiou, M., and Zwart, B. (2019). A stochastic resource-sharing network for electric vehicle charging. IEEE Transactions on Control of Network Systems, 6(3), 1050–1061.
[7] Zhang, X., et al. (2020). Deep-learning-based probabilistic forecasting of electric vehicle charging load with a novel queuing model. IEEE Transactions on Cybernetics, 51(6), 3157–3170.
[8] Asensio, O. I., Lawson, M. C., and Apablaza, C. Z. (2021). Electric vehicle charging stations in the workplace with high-resolution data from casual and habitual users. Scientific Data, 8, 168.
[9] Zhao, Z. and Lee, C. K. M. (2021). Dynamic pricing for EV charging stations: A deep reinforcement learning approach. IEEE Transactions on Transportation Electrification, 8(2), 2456–2468.
[10] Ma, T. and Faye, S. (2022). Multistep electric vehicle charging station occupancy prediction using mixed LSTM neural networks. Energy, 244, 123217.
[11] Yi, Z., Liu, X. C., Wei, R., Chen, X., and Dai, J. (2022). Electric vehicle charging demand forecasting using deep learning model. Journal of Intelligent Transportation Systems, 26(6), 690–703.
[12] Wang, S., et al. (2023a). Short-term electric vehicle charging demand prediction: A deep learning approach. Applied Energy, 340, 121032.
[13] Wang, S., Chen, A.,Wang, P., and Zhuge, C. (2023b). Predicting electric vehicle charging demand using a heterogeneous spatio-temporal graph convolutional network. Transportation Research Part C: Emerging Technologies, 153, 104205.
[14] Orzechowski, A., et al. (2023). A data-driven framework for medium-term electric vehicle charging demand forecasting. Energy and AI, 14, 100267.
[15] Qu, H., Kuang, H., Wang, Q., Li, J., and You, L. (2024a). A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand prediction. IEEE Transactions on Intelligent Transportation Systems, advance online publication.
[16] Kuang, H., Zhang, X., Qu, H., You, L., et al. (2024). Unraveling the effect of electricity price on electric vehicle charging behavior: A case study in Shenzhen, China. Sustainable Cities and Society, 115, 105836.
[17] Qu, H., et al. (2024b). ChatEV: Predicting electric vehicle charging demand as natural language processing. Transportation Research Part D: Transport and Environment, 136, 104470.
[18] Baek, K., Lee, E., and Kim, J. (2024). A dataset for multi-faceted analysis of electric vehicle charging transactions. Scientific Data, 11, 262.
[19] Li, H., Qu, H., Tan, X., You, L., Zhu, R., Fan, W., et al. (2025). UrbanEV: An open benchmark dataset for urban electric vehicle charging demand prediction. Scientific Data, 12, 523.
[20] Guo, Z., et al. (2025). A city-scale and harmonized dataset for global electric vehicle charging demand analysis. Scientific Data, 12, 1254.
[21] Palaniyappan, B., et al. (2024). Dynamic pricing for load shifting: Reducing electric vehicle charging demand peaks using an optimization-based pricing mechanism. Sustainable Cities and Society, 104, 105285.
