Monday, March 17, 2025 - 4:00pm
Event Calendar Category
LIDS Seminar Series
Speaker Name
Kyri Baker
Affiliation
University of Colorado Boulder
Building and Room Number
32-155
"Optimizing Power Grids with AI: Ensuring Feasibility and Stability"
Abstract: The electric power grid, one of our country’s most complex pieces of infrastructure, is crucial to the operation of modern society. Governing the operation of this system is often guided by solving a large-scale, complex optimization problem called Optimal Power Flow (OPF). However, the grid is rapidly becoming an even more complicated system to manage: higher levels of intermittent, renewable energy; aging components and increased blackouts; increased extreme weather events; and new demands from electrification and datacenters.
This talk discusses the development of artificial intelligence (AI) models that can help solve OPF problems rapidly, to assist grid operators in diagnosing and operating issues in the grid more effectively. First, we discuss how counterfactual explanations can help grid operators understand the best path to fixing infeasibilities in the OPF problem, which are often solved manually or by time-intensive “feasibility fixing” procedures within an optimization solver. The second part of the talk discusses how AI models can be used to ensure that steady-state operating points preserve generator dynamic stability while pursuing optimal operation.
Initial results indicate that the use of AI to solve optimization problems in power grids can result in lower cost, fewer potential blackouts, and lowered carbon emissions.
Bio: Dr. Kyri Baker received her B.S., M.S., and Ph.D. in Electrical and Computer Engineering from Carnegie Mellon University in 2009, 2010, and 2014, respectively. From 2015 to 2017, she worked at the National Renewable Energy Laboratory. She is now an Associate Professor at the University of Colorado Boulder and a Fellow of the Renewable and Sustainable Energy Institute (RASEI).
She combats climate change by developing computational tools that leverage optimization and machine learning to operate energy systems more efficiently and reliably. Dr. Baker has received a National Science Foundation CAREER award for her work combining power system operations with machine learning and has led an award-winning team in the Department of Energy ARPA-E Grid Optimization competition. She is currently on sabbatical as a Visiting Researcher at Google DeepMind, working on how AI can help optimize electric power grids.