SOURCE-LINKED INTELLIGENCE

Scaling Laws for Physics-Aware ACOPF Surrogate Learning

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

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 both MSE and AL training, and characterize how constraint violation changes with network size across grids. Both objectives improve as power laws, but at different rates: MSE i

Read original source ↗ Open in workspace

recordType

paper

region

Global