报告人：香港科技大学（广州） 陈绎泽 助理教授
Title:Learning to Charge Electric Vehicles:Modeling and Decision-Making
Recent proliferation of electric vehicles encourages the design of reliable and efficient operation of EV charging networks. Such charging schemes not only hold the promise of satisfying charging needs of varying locations and time windows, but also benefiting the power grid-level carbon emissions and electricity costs.
In this talk, I will present some of our recent exploration in designing learning-enabled EV charging algorithms. First, I will present some of our current efforts on learning individual EV charging curves based on sparse patterns. Second, I will introduce how to explicitly incorporate the carbon objectives and battery state-of-charge information into the operation framework of charging station. I will show how these techniques can be generalized to a set of control problems that the learning algorithms help improve system performance. Finally, I will discuss potential research that can leverage machine learning and optimization techniques for better accommodating EVs into transportation and power networks.
Bio: Yize Chen just joined the AI Thrust at Hong Kong University of Science and Technology (Guangzhou) as an assistant professor this fall. He was a postdoc at Berkeley Lab from 2021 to 2022. He got his PhD degree in Electrical and Computer Engineering from University of Washington in 2021, and his bachelor degree from Chu Kochen College at Zhejiang University in 2016. His research interests lie at the intersection of machine learning, optimization, and control theory, with applications in energy systems and cyber-physical systems. He has received several prize paper awards including PES General Meeting, ACM e-Energy and PSCC, and held research positions in multiple institutions including Microsoft Research, Los Alamos National Laboratory and Harvard Medical School.