EUVIMEDEUVIMED entdecken
Crossref

Spatio-Temporal Graph-Based Grid Integration of Large-Scale Electric Vehicle With Heterogeneous Charging Flexibility Aggregation

Shuying Lai, Zhao Yang Dong, Yuechuan Tao, Jing Qiu, Tianjing Wang, Zhijun Zhang, Xianzhuo Sun, Junhua Zhao

IEEE Transactions on Intelligent Transportation Systems · 2026-07 · 27 (7) · 7961-7973

DOI: 10.1109/tits.2026.3670971 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-07. Verfasst von Shuying Lai und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Smart Grid-National Science and Technology Major Project, Jockey Club (JC) Science, Technology, Engineering, and Mathematics (STEM) Laboratory of Future Energy Systems, Global STEM Professorship.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While Electric Vehicles (EVs) have the potential to contribute to low-carbon transportation, the burgeoning adoption of EVs and uncoordinated charging can place a significant burden on the power grid. This paper addresses the challenges of the integration of massive EVs into smart grids by introducing a comprehensive framework with heterogeneous flexibility aggregation. First, a Spatio-Temporal Heterogeneous Graph Neural Network (STH-GNN) is proposed to accurately predict EV charging demands by analyzing complex spatio-temporal relationships. Furthermore, a bi-level coordinated charging scheduling framework optimizes grid operations and individual EV charging schedules, relieving grid burden and enhancing efficient energy use based on the STH-GNN prediction. It solves the gaps between prediction errors and real-time actual charging demand. Additionally, the EV flexibility set is modelled to effectively aggregate heterogeneous EV resources, allowing for optimized deployment of large-scale EV assets by constructing the inner approximation of the Minkowski sum of the individual flexibility sets. The proposed method is verified in simulation, utilizing data from a realistic urban setting with diverse EV charging behaviours and grid conditions. Simulations demonstrate the effectiveness of the STH-GNN in accurately forecasting EV charging demands across different times and locations. The bi-level charging scheduling framework successfully manages grid burden while showcasing significant improvements in operational efficiency and cost reduction. Results validate the proposed model’s robustness and scalability, proving its potential applicability in real-world smart grid environments.

Förderung

  • Smart Grid-National Science and Technology Major Project
  • Jockey Club (JC) Science, Technology, Engineering, and Mathematics (STEM) Laboratory of Future Energy Systems
  • Global STEM Professorship
  • Startup Grant of City University of Hong Kong
  • Huawei Technologies Company Ltd

Zitieren

APA

Lai, S., Dong, Z. Y., Tao, Y., Qiu, J., Wang, T., Zhang, Z., Sun, X., & Zhao, J. (2026). Spatio-Temporal Graph-Based Grid Integration of Large-Scale Electric Vehicle With Heterogeneous Charging Flexibility Aggregation. IEEE Transactions on Intelligent Transportation Systems, 27(7), 7961-7973. https://doi.org/10.1109/tits.2026.3670971

Vancouver

Lai S, Dong ZY, Tao Y, Qiu J, Wang T, Zhang Z, et al. Spatio-Temporal Graph-Based Grid Integration of Large-Scale Electric Vehicle With Heterogeneous Charging Flexibility Aggregation. IEEE Transactions on Intelligent Transportation Systems. 2026;27(7):7961-7973. doi:10.1109/tits.2026.3670971

BibTeX
@article{Lai2026,
  author = {Lai, Shuying and Dong, Zhao Yang and Tao, Yuechuan and Qiu, Jing and Wang, Tianjing and Zhang, Zhijun and Sun, Xianzhuo and Zhao, Junhua},
  title = {Spatio-Temporal Graph-Based Grid Integration of Large-Scale Electric Vehicle With Heterogeneous Charging Flexibility Aggregation},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2026},
  volume = {27},
  number = {7},
  pages = {7961--7973},
  doi = {10.1109/tits.2026.3670971}
}
Kostenlos starten →