LANS Seminar

Seminar Title: Solving AC-Optimal Power Flow in the era of AI: Challenges, Opportunities, and Case Studies on Korea Power Grid

Speaker: Hongseok Kim, Professor, Department of Electronic Engineering at Sogang University

Date/Time: Thursday, February 13, 2025/ 2:30 PM – 3:30 PM (In-Person)
Location: See Meeting URL on the cels-seminars website which will require an Argonne login.

Description: Conventional solvers are often computationally expensive for constrained optimization, particularly in large-scale and time-critical problems including AC optimal power flow (OPF) problems. While this leads to a growing interest in using neural networks (NNs) as fast optimal solution approximators, incorporating the constraints with NNs is challenging. In this regard, we present deep Lagrange dual with equation embedding (DeepLDE), a framework that learns to find an optimal solution without using labels. To ensure feasible solutions, we embed equality constraints into the NNs and train the NNs using the primal-dual method to impose inequality constraints. The equality constraints correspond to power flow equations, and the inequality constraints include the operational limits of generators and transmission lines. We prove the convergence of DeepLDE and show that the previous primal-dual learning method cannot solely ensure equality constraints without the help of equation embedding. Simulation results on non-convex and AC-OPF problems show that the proposed DeepLDE achieves the smallest optimality gap among all the NN-based approaches while always ensuring feasible solutions. Furthermore, the computation time of the proposed method is up to 35 times faster than the baselines in solving constrained non-convex optimization, and/or AC-OPF. In addition to the test on the PGLib 1354-bus system, we demonstrate the results using real national grid data provided by KPX, the sole ISO in Korea, where the number of buses is 4,872. Our findings show that DeepLDE is scalable and applicable to real power systems, highlighting its potential for AI-based optimization with implicit layers. Based on our experience with the Korean power grid, we discuss how to implement AI-based optimization for real-time operation, where grid topology frequently changes.

Bio: Dr. Hongseok Kim is a Professor in the Department of Electronic Engineering at Sogang University. He received his B.S. and M.S. degrees in the School of Electrical Engineering from Seoul National University, South Korea, and his Ph.D. degree in the Department of Electrical and Computer Engineering at The University of Texas at Austin, USA. He was a Post Doctoral Research Associate at Princeton University, and a Member of Technical Staff at Bell Laboratories Alcatel-Lucent, Murray Hill, USA. His current research interests include AI and machine learning, optimization and resource management in networks, specifically focused on energy ICT, power systems, smart grid communications, wireless networks and economics. Dr. Hongseok Kim is one of the two recipients of the Korea Government Oversea Scholarship during 2005-2008. He received the Haedong Young Professor Award in 2016. He has been an IEEE Senior Member since 2016.

Please note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.