Vlad Dvorkin, University of Michigan, Electrical and Computer Engineering
Location: EECS 1311
Time: 3:30 PM – 4:30 PM
Abstract:
Power grid operations have been profoundly influenced by innovations in data analytics, optimization, and control — all thriving on the availability of power grid data and models. However, as power grids contain much proprietary data and increasingly become targets of cyberattacks, releasing information from power systems now requires carefully balancing grid transparency, data owner privacy, and security objectives. The last two are often prioritized by conservative grid operators at the expense of the former. How can we systematically balance grid transparency with the privacy and cyber resilience of power systems?
In this talk, I will provide algorithmic answers to this question that quantify and control information disclosures from power systems while ensuring that the source system and its actors are not exposed to cyber and privacy risks. They are based on the fusion of power grid engineering, operations research, differential privacy, and diffusion models, various combinations of which enable controllable data disclosures in various contexts. Our solutions aim to set new standards for trustworthy data sharing in the power systems industry, enabling frequent and targeted data sharing, creating new opportunities for third-party analytics, and enabling public oversight of grid and market operations.
Biography:
Vladimir Dvorkin is an Assistant Professor in the Electrical Engineering and Computer Science Department at the University of Michigan. He has held positions as a postdoctoral fellow at the Massachusetts Institute of Technology’s Energy Initiative and LIDS from 2021–2023, and as a visiting researcher at Georgia Tech’s School of Industrial and Systems Engineering. He received his Ph.D. in Electrical Engineering from the Technical University of Denmark in 2021. His research focuses on power systems design, operation, and control, viewed through the lenses of optimization and machine learning, energy economics, and algorithmic data privacy. His work has received numerous recognitions, including the Marie Skłodowska-Curie Actions postdoctoral fellowship, the IEEE Transactions on Power Systems Best Paper Award, and the INFORMS ENRE Early Career Best Paper Award.