Scaling Laws for Physics-Aware ACOPF Surrogate Learning

Year: 2026

Type: preprint

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 $19\times$ with $2.4\times$ the training time and negligible added memory. The training objective shapes not only where a surrogate lands but how its quality evolves with scale.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.16282

Authors: Li, Yijiang, Dey, Emon, Fenu, Stefano, Pasini, Massimiliano Lupo, Kuruganti, Teja, Kim, Kibaek

Institutions: Argonne National Laboratory, Oak Ridge National Laboratory

Topic: Optimal Power Flow Distribution

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, University of Chicago, Office of Science, Advanced Scientific Computing Research, Argonne National Laboratory, Oak Ridge National Laboratory

OpenAlex ID: W7213408373