Learning and Control for Large-scale Sustainable Energy Systems

Abstract 
Sustainable energy systems hold the promise to significantly reduce negative environmental impact and improve economic and social welfare. However, as these energy systems continue to expand in scale, complexity, and interconnectivity, the associated technical challenges also intensify. For example, desirable system behaviors must be maintained despite system uncertainties and frequent changes induced by the unpredictable nature of renewable energy sources. In this talk, I introduce a novel set-based online adaptive control framework that leverages online learning techniques (e.g., convex online optimization) and control methods (e.g., distributed control and MPC) to address unique challenges in large-scale sustainable energy systems. I will focus on the problem of learning to control systems under non-stochastic and potentially adversarial disturbances. I will present the first distributed learning-based controller that provably achieves adversarial stabilization (bounding the worst-case transient behavior during learning) for networked systems under communication delays. To further demonstrate the framework, I will describe an application to the voltage control problem for distribution grids with unknown topology. 

Bio
Jing Yu is a final-year PhD candidate in Control and Dynamical Systems at Caltech, advised by John Doyle and Adam Wierman. She is broadly interested in the interplay between control theory and machine learning, with a focus on online decision making and distributed algorithms for large-scale sustainable energy systems. She received the best paper finalist award in ACM e-energy 2022 and was named the Amazon AI4Science fellow in 2023.