Research Significance and Objectives
Promoting the deep integration of charging infrastructure, buildings, the power grid, energy storage, and microgrids can effectively improve the local consumption of distributed energy, reduce the impact of charging facilities on the power grid, support the development of new power systems and the achievement of China’s dual-carbon goals, and advance vehicle–grid interaction and virtual power plants from pilot demonstrations to regular commercial operation.
Core Methods
1. Generative large models and digital twins: Develop high-fidelity digital twin systems at the campus and urban scales.
2. Efficient and transferable reinforcement learning algorithms: Enable fast optimization of energy management strategies and support flexible transfer across different energy systems.
3. Internet of Vehicles and microgrid interconnection technologies: Enable bidirectional V2G energy interaction between electric vehicles, microgrids, and the power grid.
Application Scenarios
This research can be applied to transportation energy system optimization and scheduling, V2G/V2B strategy optimization, smart campus energy management, energy demand and load forecasting, emergency impact simulation, demand response strategy simulation, peak shaving and valley filling, and congestion mitigation.
Collaboration Partners
Hubei Kaijia Energy Technology Group
Tohoku University, Japan
Guangzhou International Campus, South China University of Technology
Research Achievements
Li W, Lin Z, Ou S*, et al. Deployment priority of public charging speeds for increasing battery electric vehicle usability. Transportation Research Part D: 2023. JCR Q1, IF 7.7
Yang Z, Chen Y, Ou S*. From LLM to Deep Learning: Efficient Simulation of Last-Mile Energy Behavior in Campus Communities. WCX SAE World Congress Experience, 2026. EI
Chen Y, Yang Z, Ou S*. Generative Agents for High-Fidelity Simulation of Community-Scale Mobility and Energy Behavior. WCX SAE World Congress Experience, 2026. E