I am currently an assistant professor at Department of Electrical and Computer Engineering at the University of Alberta. Previously, I held a tenure-track position at AI Thrust, Information Hub at Hong Kong University of Science and Technology (Guangzhou), also affiliated with the Department of Computer Science and Engineering at HKUST. In my research, I focus on the intersection between control, optimization and machine learning, and I am interested in designing cyber-physical systems especially power systems with performance guarantees. I am committed to achieving sustainable and autonomous clean energy systems.
I was fortunate to work with Baosen Zhang and get my Ph.D. in Electrical and Computer Engineering from University of Washington in 2021; and my undergraduate degrees in Automation from Chu Kochen College at Zhejiang University in 2016. I was also a postdoc researcher at the Computing Sciences Area of Berkeley Lab from 2021 to 2022 and part of the Berkeley Lab Cybersecurity R&D for Science and Energy. From 2023 to 2024, I also worked as an analyst in Advanced Technology Solutions group at ISO New England. Here is my CV (last update June 2024). I have also held research positions at Microsoft Research, Los Alamos National Laboratory, and Harvard Medical School, working on a set of problems related to data centers, power grid infrastructures, biological dynamics and built environment. Our works have been recognized worldwide, and received several best paper and prize paper awards at IEEE PES General Meeting (2024, 2022), Power Systems Computation Conference (PSCC) (2020), and ACM e-Energy (2019).
We have 2-3 openings for graduate students (for both MSc and PhD levels) in our group. If you are interested in the general areas of control and optimization, power and energy systems, and machine learning, please drop me an email with your research interests and related experiences. Students from all identities and backgrounds are encouraged to apply.
News
Jun 2024 Paper in IEEE Transactions on Power Systems: "Long-Term Carbon-Efficient Planning for Geographically Shiftable Resources: A Monte Carlo Tree Search Approach". We look into the flexibility potential of demands in reducing long-term power grid carbon emissions. A MCTS-based efficient search approach is also developed.
May 2024 Work presented at ACM e-Energy 2024: "Contributions of Individual Generators to Nodal Carbon Emissions". We propose a real-time solution for quantifying the locational average and marginal emissions in power grids. This algorithm can be used for fine-grained carbon auditing and carbon-emission based energy system operations.
December 2023 Papers at NeurIPS 2023: Two papers accepted at this year's NeurIPS conference. In "Adjustable Robust Reinforcement Learning for Online 3D Bin Packing", we propose a robust RL framework for solving bin-packing problem, and such robust formulation is also generalizable for RL and combinatorial problems; In "SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems", we propose and benchmark a set of physics-driven, high-fidelity reinforcement learning environments suitable for power and energy systems, which are also publicly available.
Email:
Address:
11-351 Donadeo Innovation Centre For Engineering
9211 116 St NW,
Edmonton, AB
Tel: 1-825-965-8817
