Mingyu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mingyu Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Fengjie Li
School of Cyber Security and Computer, Hebei University, Baoding, China
3 shared publications - Hong Zhang
Hebei University
3 shared publications - Liqiang Wang
University of Central Florida
2 shared publications - Miao Wang
School of Cyber Security and Computer, Hebei University, Baoding, China
2 shared publications - Zhibo Sun
Drexel University, Philadelphia, USA
1 shared publication
Latest Publications
- 10 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
RVGCL: Towards robust recommendation via graph contrastive learning with variational inference
- 10 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
RVGCL: Towards robust recommendation via graph contrastive learning with variational inference
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (1) , 1322-1338
ECO-V2G: Joint Optimization of EV Charging, Discharging, and Task Offloading in V2G Networks With Heuristic McCormick
The increasing number of electric vehicles (EVs), along with advances in battery and onboard computing technologies, has enabled EVs to gradually serve as energy carriers and computational nodes in urban vehicular networks. However, factors such as dynamic pricing in energy markets and uneven demand distribution have led to spatiotemporal fluctuations in charging station loads and electricity prices, posing new challenges for the efficient management of EV charging/discharging and routing in urban environments. To address these challenges, we propose a unified framework called ECO-V2G, in which charging stations are enhanced with both energy trading and edge computing capabilities, forming an integrated edge charging station (ECS) network. Within this framework, we first design a bidirectional spatiotemporal graph transformer to accurately predict the real-time load and electricity prices of ECSs. The predictions are then incorporated into a mixed-integer nonlinear programming (MINLP) problem that jointly optimizes EV routing, charging/discharging, and task offloading decisions, which is efficiently solved on a state transition network using a McCormick-based heuristic algorithm. Finally, we conduct extensive simulations to validate the effectiveness of the proposed ECO-V2G framework. Experimental results show that it reduces EV user travel costs by up to 39.41% compared to state-of-the-art baselines, highlighting its effectiveness in complex urban scenarios.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (1) , 1322-1338
ECO-V2G: Joint Optimization of EV Charging, Discharging, and Task Offloading in V2G Networks With Heuristic McCormick
The increasing number of electric vehicles (EVs), along with advances in battery and onboard computing technologies, has enabled EVs to gradually serve as energy carriers and computational nodes in urban vehicular networks. However, factors such as dynamic pricing in energy markets and uneven demand distribution have led to spatiotemporal fluctuations in charging station loads and electricity prices, posing new challenges for the efficient management of EV charging/discharging and routing in urban environments. To address these challenges, we propose a unified framework called ECO-V2G, in which charging stations are enhanced with both energy trading and edge computing capabilities, forming an integrated edge charging station (ECS) network. Within this framework, we first design a bidirectional spatiotemporal graph transformer to accurately predict the real-time load and electricity prices of ECSs. The predictions are then incorporated into a mixed-integer nonlinear programming (MINLP) problem that jointly optimizes EV routing, charging/discharging, and task offloading decisions, which is efficiently solved on a state transition network using a McCormick-based heuristic algorithm. Finally, we conduct extensive simulations to validate the effectiveness of the proposed ECO-V2G framework. Experimental results show that it reduces EV user travel costs by up to 39.41% compared to state-of-the-art baselines, highlighting its effectiveness in complex urban scenarios.