Workshops Archive

Scaling Laws for Physics-Aware ACOPF Surrogate Learning


Workshop: AI4S: 8th Workshop on Artificial Intelligence and Machine Learning for Scientific Applications

Authors: Yijiang Li, Emon Dey, and Stefano Fenu (Argonne National Laboratory); Massimiliano Lupo Pasini and Teja Kuruganti (Oak Ridge National Laboratory); and Kibaek Kim (Argonne National Laboratory)

Abstract: Learning-based surrogates for AC optimal power flow (ACOPF) promise large speedups over classical solvers, but their operational value depends on physical feasibility as much as predictive accuracy. Physics-aware objectives such as the augmented Lagrangian (AL) improve constraint satisfaction at additional per-step cost, yet how this trade-off behaves with scale is uncharacterized. We sweep model and dataset sizes under MSE and AL training, and measure how violation changes with network size. Both objectives improve as power laws: MSE prediction loss depends more on model size than on data, while the AL composite of prediction loss and violation improves comparably along both axes. Violation grows markedly more slowly with network size under AL. On matched hardware and equal training samples, AL reduces violation about 19x with 2.4x training time and negligible added memory. The training objective shapes not only where a surrogate lands but how its quality evolves with scale.


Back to AI4S: 8th Workshop on Artificial Intelligence and Machine Learning for Scientific Applications Archive Listing

Back to Full Workshop Archive Listing