Abstract:  Power grids are undergoing rapid change: adoption of customer-owned devices like rooftop solar and EVs, increased penetration of renewable generation, and emerging large loads including AI data centers. Amidst these changes, grid operators and planners must ensure secure and reliable infrastructure across generation, transmission, and distribution. These challenges translate directly to power systems decision-making: to ensure there is sufficient generation capacity to meet demand, transmission capacity to deliver power to load centers, and operational flexibility to accommodate diverse load patterns and intermittent renewable generation. All of these problems must be solved at an industry-scale of tens of thousands of buses, which can be challenging for traditional algorithms. This talk will explore our efforts in developing scalable and robust optimization and ML algorithms for power systems planning and operations, deploying techniques including distributed optimization, machine learning, and regularized Benders.

 

 

Bio: Rabab Haider is an Assistant Professor of Civil and Environmental Engineering at the University of Michigan. Her research is centered on designing future energy systems that provide green, reliable, and affordable energy for All. Her group develops optimization and AI algorithms that advance energy system operations, planning, and market under deep decarbonization. She received her Ph.D. and S.M. degrees at MIT, and B.A.Scin Engineering Science at the University of Toronto. She was previously named a MIT Energy Fellow and MathWorks-MIT Mechanical Engineering Fellow. Dr. Haider is also an Affiliate Faculty at the Georgia Institute of Technology and NSF AI Institute for Advances in Optimization (AI4OPT).