⏻ptiML
/ˈɑp·tə·məl/
Optimizing energy. Empowering society.
The OptiML group develops principled algorithms for modern power grids at the intersection of power engineering, optimization, machine learning, and economics. We cast grid operations and electricity markets under uncertainty as structured optimization–learning problems, integrating ML into optimization to improve decisions, and using optimization to discipline ML for reliability and interpretability. We advance grid analytics for high-stakes operations, study the integration of AI as both software (models, analytics) and hardware (data centers) within grid constraints, and design feedback mechanisms for grid–AI–grid interaction. We also develop rigorous methods for energy data privacy and security, enabling controllable transparency with provable guarantees for agent privacy and system integrity.
Postdoctoral Researchers
Zhirui Liang is a Schmidt AI in Science Postdoctoral Research Fellow at Michigan Institute for Data and AI in Society (MIDAS), University of Michigan, under the mentorship of Prof. Vladimir Dvorkin and Prof. Jiasi Chen. She investigates the challenges and opportunities of integrating AI and data centers with modern power grids, addressing their substantial electricity consumption while leveraging their inherent spatial-temporal load-shifting flexibility.
PhD Students
Milad is a Ph.D. candidate in the Department of Electrical Engineering and Computer Science at the University of Michigan. He received his M.Sc. and B.Sc. degrees in Electrical Engineering from Tarbiat Modares University and Babol Noshirvani University of Technology, respectively. His research develops data-driven decision-making tools for modern power and energy systems with rigorous guarantees on uncertainty, robustness, and privacy, drawing methodologically on generative models, conformal prediction, sequential inference, and differential privacy. He is currently developing a sequential changepoint detection framework for anomaly detection in power systems to enable timely and reliable identification of emerging system-wide events.
Shengyang Wu grew up in Zhejiang, China. He received his B.S. degree in Electrical Engineering from North China Electric Power University (NCEPU) in 2021 and his M.S. degree in Electrical Engineering from Huazhong University of Science and Technology (HUST) in 2024. He is currently pursuing a Ph.D. under the supervision of Professor Vladimir Dvorkin. His research focuses on power system optimization and control, with particular interest in differential privacy for the secure release of sensitive grid datasets. His work aims to enhance transparency in power systems while preserving the privacy of system operators and market participants.
Xinwei Liu is a Ph.D. candidate in Electrical and Computer Engineering at the University of Michigan, advised by Prof. Vladimir Dvorkin. Before joining Michigan, Xinwei earned an M.S. in Aerospace Engineering from Stanford University and a B.S. in Mechanical Engineering from Cornell University. Xinwei’s research focuses on integrating real-time power system frequency dynamics with electricity market operations. Currently, Xinwei is developing online pricing mechanisms that leverage instantaneous frequency measurements to inform electricity prices, addressing the mismatch between fast grid signals and the slower pace of traditional real-time markets. Xinwei is also providing rigorous market properties for these mechanisms.
Yanyong Mao is pursuing a PhD in Electrical Engineering at the University of Michigan. He received his Bachelor’s degree in Electrical Engineering from Shanghai Jiao Tong University in 2024. His research interests include the integration of data centers and AI loads in power systems, distributed energy resources, and power system control. He is currently working on a project on electric vehicle charging flexibility, co-advised by Professors Vladimir Dvorkin and Johanna Mathieu. He is enthusiastic about the electrification and decarbonization of human society. In his free time, he enjoys music, movies, and traveling.
Megan is a second year PhD student in the School for Environment and Sustainability at the University of Michigan on a dual track for a second degree in the Electrical Engineering program. She holds bachelor's degrees in Mechanical Engineering and Physics from UCLA. Raised on environmentalist ideals and directly exposed to the expansive dangers climate change poses to humanity, Megan is pursuing a PhD with the intention to engage in transformative, interdisciplinary research addressing the current existential problem facing our species. Her current research focuses on incorporating climate impact on transmission systems into capacity expansion modeling and investigating the mitigation potential of grid-enhancing technologies.
Wei is a second-year Ph.D. student in Environment & Sustainability and Electrical & Computer Engineering at the University of Michigan. He works as a research assistant in the ASSET Lab led by Prof. Michael Craig and is co-advised by Prof. Vladimir Dvorkin. He earned his Bachelor’s degree in Energy and Power Engineering from Tsinghua University and his Master’s degree in Engineering Thermophysics from the University of Chinese Academy of Sciences, where his research focused on thermo-mechanical energy storage. Driven by a growing interest in macro-energy systems, he joined the University of Michigan to pursue his Ph.D. His current research centers on seasonal hydrogen storage and natural gas infrastructure retrofitting through the development of sector-coupled capacity expansion models.
Master Students
Renjian Ruan 2025 ML-based generator frequency control in transmission systems
Hyun June Kim 2024 Synthesizing data for linear programming
Undergraduate Students
Saniya Kalamkar 2026 Controlling distribution voltage under LLM training loads
Ian Beeck 2025/26 Current affairs: An interactive electricity market game
Shriramu Ramesh 2024/25 Current affairs: An interactive electricity market game
Thomas Payne 2024/25 Current affairs: An interactive electricity market game