Xiangyu Zhang
Researcher III-Applied Mathematics
Xiangyu.Zhang@nrel.gov
303-275-4068
Google Scholar
ResearchGate
Xiangyu Zhang is a researcher from the AI, Learning and Intelligent Systems group in the Computational Science Center. Since he joined NREL in 2019, his research interests mainly focus on learning-based optimal control for energy systems, including computational techniques like classic optimization, reinforcement learning, differentiable programming, and hybrid methods. Given his background in power system engineering, his research aims at developing advanced and practical solutions for smart grid, especially on applications for demand response and grid resilience enhancement. Xiangyu has worked on and played key role in multiple research projects that are funded by various U.S. Department of Energy offices, including the Building Technologies Office, Solar Energy Technologies Office, Vehicle Technologies Office, and the Office of Electricity.
Research Interests
Learning-based optimal control for energy systems
Smart grid demand response
Grid resilience
Education
Ph.D., Electrical Engineering, Virginia Tech
M.S., Electrical Engineering, Tsinghua University
B.S., Electrical Engineering, Wuhan University
Professional Experience
Researcher III, NREL (2021–present)
Postdoctoral Researcher, NREL (2019–2021)
Software Developer Summer Intern, Google Nest (2018)
Graduate Research Assistant, Virginia Tech (2015–2018)
Graduate Teaching Assistant, Virginia Tech (2014–2015)
Associations and Memberships
Senior Member, Institute of Electrical and Electronics Engineers (IEEE)
Featured Work
Publications
Curriculum-based Reinforcement Learning for Distribution System Critical Load Restoration, IEEE Transactions on Power Systems (2022)
Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control, IEEE Transactions on Smart Grid (2022)
Double-signal Retail Pricing Scheme for Acquiring Operational Flexibility from Batteries, IEEE Transactions on Sustainable Energy (2021)
An Edge-Cloud Integrated Solution for Buildings Demand Response Using Reinforcement Learning, IEEE Transactions on Smart Grid (2020)
Learning-Accelerated ADMM for Distributed DC Optimal Power Flow, IEEE Control Systems Letters (2020)
An IoT-Based Thermal Model Learning Framework for Smart Buildings, IEEE Internet of Things Journal (2019)
Software
Reinforcement Learning Controller for Critical Load Restoration Problems (GitHub)
Learning Building Control (GitHub)
Powergridworld: A Framework for Multi-agent Reinforcement Learning in Power Systems (GitHub)
Share