Date: 6 March 2026, Friday
Time: 04:30 PM
Venue: FYW-3316, Fong Yun Wah Building, City University of Hong Kong
Zoom Meeting ID: 859 8869 4437
Password: 123456
Speaker: Dr Biwei Li, City University of Hong Kong
Abstract: Accurate power flow forecasting is crucial for enabling timely interventions to prevent cascading failure events from escalating into large-scale outages. This talk presents a spatio-temporal learning model specifically designed for forecasting power flow redistribution during cascading failure events. The model combines a Transformer-based temporal encoder with a Graph Transformer network to jointly capture the temporal evolution and spatial dependencies within the grid, thereby enhancing robustness under rapidly changing operating conditions. The proposed model is evaluated on the IEEE 118-bus system and compared against several state-of-the-art baselines, demonstrating superior accuracy across short- and long-term forecasting. By accurately forecasting abrupt flow surges across branches, the model supports early identification of vulnerable components and high-risk regions over time. Finally, we introduce a mitigation strategy informed by the power flow forecasting model. Leveraging long-horizon forecasts, the proposed mitigation strategy effectively reduces large outages and circumvents intervention-induced failure.
Speaker’s Bio: Biwei Li is currently a research assistant at the City University of Hong Kong, Hong Kong. She received the B.Eng. degree in mechanical engineering from China University of Geosciences, Wuhan, China, in 2015, the M.Eng. degree in control science and engineering from Beihang University, Beijing, China, in 2018, and the Ph.D. degree in electrical engineering from City University of Hong Kong, Hong Kong, in 2026. Her research interests include complex networks, deep learning applications, and robust analysis of power networks.
WEBINAR WEBSITE:
https://www.ee.cityu.edu.hk/~cccn/
https://www.ee.cityu.edu.hk/~cccn/centre-seminars.htm