EUVIMEDEUVIMED entdecken
Crossref

EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction

Feng Lyu, Shiwen Wu, Sijing Duan, Zeyang Tang, Mingliu Liu, Manjia Liu, Wei Rao, Yiwen Li

IEEE Transactions on Intelligent Transportation Systems · 2026-10 · 27 (10) · 12216-12232

DOI: 10.1109/tits.2026.3704750 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-10. Verfasst von Feng Lyu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electric vehicles (EVs) charging demand prediction is crucial for regional load scheduling, dynamic pricing, and charging infrastructure planning. Although existing studies have made some efforts, they mainly focus on a single type of vehicle (e.g., buses or taxis) and seldom consider the correlations between different vehicle types and their collective impacts (e.g., vehicle mobility) on regional charging demand. Therefore, these models may cause performance degradation when applied in practical settings where multiple types of EVs coexist. To fill this gap, we design a novel multi-task learning framework EVCha with heterogeneous multi-graph fusion to enable collaborative charging demand prediction for multi-types of EVs. Firstly, a multi-type vehicle shared feature extraction module is designed to extract and fuse similar patterns of different vehicles. Secondly, a heterogeneous multi-graph spatio-temporal learning module is developed to capture multiple dependency relationships, including historical charging demand similarity, vehicle mobility, and points of interest distribution among regions. Thirdly, an MTL-based training module is designed to achieve collaborative prediction of multi-type EVs. We evaluate EVCha using two large-scale real-world datasets. Extensive experimental results show that EVCha achieves superior performance and outperforms the state-of-the-art baseline by 22.5% in root mean square error. The source code and data are available at https://github.com/charging-demand/EVCha.

Zitieren

APA

Lyu, F., Wu, S., Duan, S., Tang, Z., Liu, M., Liu, M., Rao, W., & Li, Y. (2026). EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction. IEEE Transactions on Intelligent Transportation Systems, 27(10), 12216-12232. https://doi.org/10.1109/tits.2026.3704750

Vancouver

Lyu F, Wu S, Duan S, Tang Z, Liu M, Liu M, et al. EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction. IEEE Transactions on Intelligent Transportation Systems. 2026;27(10):12216-12232. doi:10.1109/tits.2026.3704750

BibTeX
@article{Lyu2026,
  author = {Lyu, Feng and Wu, Shiwen and Duan, Sijing and Tang, Zeyang and Liu, Mingliu and Liu, Manjia and Rao, Wei and Li, Yiwen},
  title = {EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2026},
  volume = {27},
  number = {10},
  pages = {12216--12232},
  doi = {10.1109/tits.2026.3704750}
}
Kostenlos starten →