Session Title: Data-Driven Approaches for Flexible Resources Utilization in Sustainable Urban Power Systems
The transition towards sustainable and decarbonized urban power systems requires the effective integration and coordinated utilization of a diverse portfolio of flexible energy resources, which mainly includes distributed renewable generation, energy storage systems and flexible load based on Electric Vehicle(EV). Harnessing the full potential of these flexible resources is critical for enhancing the resilience, reliability, and efficiency of future smart city power networks. However, the large-scale, heterogeneous, and intermittent nature of these flexible assets presents significant challenges in terms of monitoring, forecasting, optimization, and control. Traditional approaches are no longer sufficient, necessitating the development of advanced data-driven methodologies that can leverage the wealth of information generated by the evolving urban energy infrastructure.
- Novel data driven approach for EV charging load prediction in multiple scales of city
- Charging station siting and sizing in sustainable urban power systems
- Reinforcement learning-based coordination of EV charging and discharging for peak demand reduction and resilience improvement
- Advanced electricity grid models and tools for flexibility management
- Machine learning and optimization theory to achieve more efficient market clearing and Optimal Power Flow (OPF) algorithms
- Data analytics and game theory to quantify the trade-off among various future energy markets’ requirements.
List of topics of interest include, but are not limited to the following:
Special Session Chairs
Ying Du
Hong Kong Polytechnic University, China
Ying Du received his B.Eng. degree in electrical engineering from Central South University in 2017 and Ph.D. in electrical engineering from Shanghai Jiao Tong University in 2022. She is currently working as the Postdoctoral Fellow with Hong Kong Polytechnic University. Her research interests include fault detection, EV integration and resilience improvement in urban power systems.
Honglin Wen
Shanghai Jiao Tong University, China
Honglin Wen received the bachelor’s and Ph.D. degrees in electrical engineering from Shanghai Jiao Tong University, Shanghai, in 2017 and 2022, respectively. Now he works as a postdoc researcher at Shanghai Jiao Tong University and Imperial College London. His research interests include predictive and prescriptive analytics especially machine learning applications for power systems, energy forecasting, electricity markets, and decision making under uncertainty.