IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v384y2025ics0306261925001904.html
   My bibliography  Save this article

Explainable spatiotemporal multi-task learning for electric vehicle charging demand prediction

Author

Listed:
  • Shang, Yitong
  • Li, Duo
  • Li, Yang
  • Li, Sen

Abstract

This paper introduces an explainable multi-task learning framework designed to accurately predict zonal-level, multi-dimensional charging demand characteristics for electric vehicles (EVs), including the occupancy of charging piles, charging volumes, and charging durations. The proposed framework is structured into two interconnected phases. In the prediction phase, the study develops a temporal GraphSAGE model adept at capturing spatiotemporal nuances. This model is seamlessly integrated within the multi-task learning framework, which encompasses multiple prediction tasks – occupancy, volume, and duration – and promotes sharing of data representations across related tasks to enhance domain knowledge transfer. During the interpretation phase, the ”mask-compute-analyze” technique is employed to assess the significance of model components by nullifying corresponding inputs and evaluating their performance impacts using Shapley values. Building upon this, the approach incorporates small-world network theory, significantly reducing the computational complexities associated with the interpretability of spatial inputs across large transportation networks. Additionally, the framework adopts a dual analysis strategy, conducting both extra and intra-analysis, to comprehensively investigate extensive network effects as well as localized phenomena. The proposed method is validated through a realistic case study in Shenzhen, China, using real-world data from charging stations. We demonstrate that the multi-task learning framework not only improves the MAPE of occupancy prediction by 25.87% but also enhances the performance of volume prediction by 8.15% and duration prediction by 26.10%, compared to learning each task individually. In terms of interpretability, our analysis reveals that feature interactions during the model training process significantly boost predictive accuracy in the multi-task learning framework, while during the implementation phase, the prediction performance primarily depends on feature data directly related to the specific task. Additionally, we find that the absence of data from surrounding nodes had a negligible impact on individual nodes, attesting to the superiority and resilience of the proposed prediction framework.

Suggested Citation

  • Shang, Yitong & Li, Duo & Li, Yang & Li, Sen, 2025. "Explainable spatiotemporal multi-task learning for electric vehicle charging demand prediction," Applied Energy, Elsevier, vol. 384(C).
  • Handle: RePEc:eee:appene:v:384:y:2025:i:c:s0306261925001904
    DOI: 10.1016/j.apenergy.2025.125460
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261925001904
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.apenergy.2025.125460?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Pedregal, Diego J. & Trapero, Juan R., 2021. "Adjusted combination of moving averages: A forecasting system for medium-term solar irradiance," Applied Energy, Elsevier, vol. 298(C).
    2. Li, Haolong & Chen, Qihong & Zhang, Liyan & Liu, Li & Xiao, Peng, 2023. "Degradation prediction of proton exchange membrane fuel cell based on the multi-inputs Bi-directional long short-term memory," Applied Energy, Elsevier, vol. 344(C).
    3. Ren, Fei & Tian, Chenlu & Zhang, Guiqing & Li, Chengdong & Zhai, Yuan, 2022. "A hybrid method for power demand prediction of electric vehicles based on SARIMA and deep learning with integration of periodic features," Energy, Elsevier, vol. 250(C).
    4. Sahar Koohfar & Wubeshet Woldemariam & Amit Kumar, 2023. "Prediction of Electric Vehicles Charging Demand: A Transformer-Based Deep Learning Approach," Sustainability, MDPI, vol. 15(3), pages 1-17, January.
    5. Liu, Ke & Liu, Yanli, 2023. "Stochastic user equilibrium based spatial-temporal distribution prediction of electric vehicle charging load," Applied Energy, Elsevier, vol. 339(C).
    6. Li, Yuwei & Peng, Genbo & Du, Tong & Jiang, Liangliang & Kong, Xiang-Zhao, 2024. "Advancing fractured geothermal system modeling with artificial neural network and bidirectional gated recurrent unit," Applied Energy, Elsevier, vol. 372(C).
    7. Yuan, Hong & Ma, Minda & Zhou, Nan & Xie, Hui & Ma, Zhili & Xiang, Xiwang & Ma, Xin, 2024. "Battery electric vehicle charging in China: Energy demand and emissions trends in the 2020s," Applied Energy, Elsevier, vol. 365(C).
    8. Ma, Tai-Yu & Faye, Sébastien, 2022. "Multistep electric vehicle charging station occupancy prediction using hybrid LSTM neural networks," Energy, Elsevier, vol. 244(PB).
    9. Majidpour, Mostafa & Qiu, Charlie & Chu, Peter & Pota, Hemanshu R. & Gadh, Rajit, 2016. "Forecasting the EV charging load based on customer profile or station measurement?," Applied Energy, Elsevier, vol. 163(C), pages 134-141.
    10. Saikia, Pranaynil & Bastida, Héctor & Ugalde-Loo, Carlos E., 2024. "An effective predictor of the dynamic operation of latent heat thermal energy storage units based on a non-linear autoregressive network with exogenous inputs," Applied Energy, Elsevier, vol. 360(C).
    11. Abid, Md. Shadman & Ahshan, Razzaqul & Al Abri, Rashid & Al-Badi, Abdullah & Albadi, Mohammed, 2024. "Techno-economic and environmental assessment of renewable energy sources, virtual synchronous generators, and electric vehicle charging stations in microgrids," Applied Energy, Elsevier, vol. 353(PA).
    12. Zhong, Weiyi & Zhai, Dengshuai & Xu, Wenran & Gong, Wenwen & Yan, Chao & Zhang, Yang & Qi, Lianyong, 2024. "Accurate and efficient daily carbon emission forecasting based on improved ARIMA," Applied Energy, Elsevier, vol. 376(PA).
    13. Genov, Evgenii & Cauwer, Cedric De & Kriekinge, Gilles Van & Coosemans, Thierry & Messagie, Maarten, 2024. "Forecasting flexibility of charging of electric vehicles: Tree and cluster-based methods," Applied Energy, Elsevier, vol. 353(PA).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Tung Linh Nguyen & Quynh Anh Nguyen, 2025. "A Multi-Objective PSO-GWO Approach for Smart Grid Reconfiguration with Renewable Energy and Electric Vehicles," Energies, MDPI, vol. 18(8), pages 1-15, April.
    2. Yifeng Liu & Meng Chen & Pingfan Wang & Yingxiang Wang & Feng Li & Hui Hou, 2025. "A Review of Carbon Reduction Pathways and Policy–Market Mechanisms in Integrated Energy Systems in China," Sustainability, MDPI, vol. 17(7), pages 1-25, March.
    3. Mohammed Gronfula & Khairy Sayed, 2025. "AI-Driven Predictive Control for Dynamic Energy Optimization in Flying Cars," Energies, MDPI, vol. 18(7), pages 1-35, April.
    4. Zhen Chen & Ming-Ting Chen & Shu-Wei Jia, 2025. "Simulation and Optimization of New Energy Vehicles Promotion Policy Strategies Considering Energy Saving, Carbon Reduction, and Consumers’ Willingness Based on System Dynamics," Sustainability, MDPI, vol. 17(7), pages 1-23, March.
    5. Dawei Wang & Hanqi Dai & Yuan Jin & Zhuoqun Li & Shanna Luo & Xuebin Li, 2025. "Employing Quantum Entanglement for Real-Time Coordination of Distributed Electric Vehicle Charging Stations: Advancing Grid Efficiency and Stability," Energies, MDPI, vol. 18(11), pages 1-27, June.
    6. Bingxu Zhai & Yuanzhuo Li & Wei Qiu & Rui Zhang & Zhilin Jiang & Wei Wang & Tao Qian & Qinran Hu, 2025. "Physics-Informed Multi-Agent DRL-Based Active Distribution Network Zonal Balancing Control Strategy for Security and Supply Preservation," Energies, MDPI, vol. 18(11), pages 1-19, June.
    7. Jie Li & Yafei Li & Xiuli Wang & Hengyuan Zhang & Yunpeng Xiao, 2025. "Low-Carbon Economic Model of Multi-Energy Microgrid in a Park Considering the Joint Operation of a Carbon Capture Power Plant, Cooling, Heating, and Power System, and Power-to-Gas Equipment," Energies, MDPI, vol. 18(11), pages 1-20, June.
    8. Jiangfan Yuan & Min Zhang & Hongxun Tian & Xiangyu Guo & Xiao Chang & Tengxin Wang & Yingjun Wu, 2025. "A Fast-Converging Virtual Power Plant Game Trading Model Based on Reference Ancillary Service Pricing," Energies, MDPI, vol. 18(10), pages 1-19, May.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zhang, Lei & Huang, Zhijia & Wang, Zhenpo & Li, Xiaohui & Sun, Fengchun, 2024. "An urban charging load forecasting model based on trip chain model for private passenger electric vehicles: A case study in Beijing," Energy, Elsevier, vol. 299(C).
    2. Wallander, Edvin & Frank, Bobbie & Alaküla, Mats & Márquez-Fernández, Francisco J., 2025. "Full electric farming with on-field energy replenishment," Applied Energy, Elsevier, vol. 377(PA).
    3. Xu, Maosheng & Gao, Shan & Zheng, Junyi & Huang, Xueliang & Wu, Chuanshen, 2024. "Day-ahead electric vehicle charging behavior forecasting and schedulable capacity calculation for electric vehicle parking lot," Energy, Elsevier, vol. 309(C).
    4. Kreft, Markus & Brudermueller, Tobias & Fleisch, Elgar & Staake, Thorsten, 2024. "Predictability of electric vehicle charging: Explaining extensive user behavior-specific heterogeneity," Applied Energy, Elsevier, vol. 370(C).
    5. Byungsung Lee & Haesung Lee & Hyun Ahn, 2020. "Improving Load Forecasting of Electric Vehicle Charging Stations Through Missing Data Imputation," Energies, MDPI, vol. 13(18), pages 1-15, September.
    6. Boyu Xiang & Zhengyang Zhou & Shukun Gao & Guoping Lei & Zefu Tan, 2024. "A Planning Method for Charging Station Based on Long-Term Charging Load Forecasting of Electric Vehicles," Energies, MDPI, vol. 17(24), pages 1-20, December.
    7. Wang, Delu & Gan, Jun & Mao, Jinqi & Chen, Fan & Yu, Lan, 2023. "Forecasting power demand in China with a CNN-LSTM model including multimodal information," Energy, Elsevier, vol. 263(PE).
    8. Xing Zhang, 2018. "Short-Term Load Forecasting for Electric Bus Charging Stations Based on Fuzzy Clustering and Least Squares Support Vector Machine Optimized by Wolf Pack Algorithm," Energies, MDPI, vol. 11(6), pages 1-18, June.
    9. Chen, Yuanyi & Hu, Simon & Zheng, Yanchong & Xie, Shiwei & Hu, Qinru & Yang, Qiang, 2024. "Coordinated expansion planning of coupled power and transportation networks considering dynamic network equilibrium," Applied Energy, Elsevier, vol. 360(C).
    10. Buzna, Luboš & De Falco, Pasquale & Ferruzzi, Gabriella & Khormali, Shahab & Proto, Daniela & Refa, Nazir & Straka, Milan & van der Poel, Gijs, 2021. "An ensemble methodology for hierarchical probabilistic electric vehicle load forecasting at regular charging stations," Applied Energy, Elsevier, vol. 283(C).
    11. Sahar Koohfar & Wubeshet Woldemariam & Amit Kumar, 2023. "Performance Comparison of Deep Learning Approaches in Predicting EV Charging Demand," Sustainability, MDPI, vol. 15(5), pages 1-20, February.
    12. van der Meer, D.W. & Shepero, M. & Svensson, A. & Widén, J. & Munkhammar, J., 2018. "Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian Processes," Applied Energy, Elsevier, vol. 213(C), pages 195-207.
    13. Ma, Jun & Cheng, Jack C.P., 2016. "Estimation of the building energy use intensity in the urban scale by integrating GIS and big data technology," Applied Energy, Elsevier, vol. 183(C), pages 182-192.
    14. Wenjie Guo & Jie Liu & Jun Ma & Zheng Lan, 2025. "Short-Term Power Load Forecasting Using Adaptive Mode Decomposition and Improved Least Squares Support Vector Machine," Energies, MDPI, vol. 18(10), pages 1-17, May.
    15. Yang, Zhongsen & Wang, Yong & Fan, Neng & Wen, Shixiong & Kuang, Wenyu & Yang, Mou & Sapnken, Flavian Emmanuel & Narayanan, Govindasami & Li, Hong-Li, 2025. "A novel fractional order grey Euler model and its application in clean energy prediction," Energy, Elsevier, vol. 322(C).
    16. Wang, Shengyou & Li, Yuan & Shao, Chunfu & Wang, Pinxi & Wang, Aixi & Zhuge, Chengxiang, 2025. "An adaptive spatio-temporal graph recurrent network for short-term electric vehicle charging demand prediction," Applied Energy, Elsevier, vol. 383(C).
    17. Shepero, Mahmoud & Munkhammar, Joakim & Widén, Joakim & Bishop, Justin D.K. & Boström, Tobias, 2018. "Modeling of photovoltaic power generation and electric vehicles charging on city-scale: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 89(C), pages 61-71.
    18. Yu, Yang & Yu, Qinghua & Luo, RunSen & Chen, Sheng & Yang, Jiebo & Yan, Fuwu, 2024. "Degradation and polarization curve prediction of proton exchange membrane fuel cells: An interpretable model perspective," Applied Energy, Elsevier, vol. 365(C).
    19. Gonçalves, Rui & Ribeiro, Vitor Miguel & Pereira, Fernando Lobo, 2023. "Variable Split Convolutional Attention: A novel Deep Learning model applied to the household electric power consumption," Energy, Elsevier, vol. 274(C).
    20. Shafqat Jawad & Junyong Liu, 2023. "Electrical Vehicle Charging Load Mobility Analysis Based on a Spatial–Temporal Method in Urban Electrified-Transportation Networks," Energies, MDPI, vol. 16(13), pages 1-14, July.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:384:y:2025:i:c:s0306261925001904. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.