LUMINA: A Grid Foundation Model for Benchmarking AC Optimal Power Flow Surrogate Learning

TL;DR

LUMINA introduces a comprehensive benchmark suite for evaluating and improving surrogate models of AC optimal power flow, emphasizing generalization across network topologies and constraint satisfaction.

Contribution

The paper presents LUMINA-Bench, a new benchmark suite for ACOPF surrogate learning, including evaluation metrics, training objectives, and open-source tools for reproducibility.

Findings

Constraint-aware training improves robustness.

Benchmark reveals trade-offs between accuracy and constraint violations.

Open-source framework facilitates future research.

Abstract

AC optimal power flow (ACOPF) is foundational yet computationally expensive in power grid operations, driving learning-based surrogates for large-scale grid analysis. These surrogates, however, often fail to generalize across network topologies, a critical gap for deployment on grids not seen during training and for routine operational what-if studies. We introduce LUMINA-Bench, a comprehensive benchmark suite for ACOPF surrogate learning covering multi-topology pretraining, transfer, and adaptation. The benchmark evaluates homogeneous and heterogeneous architectures under single- and multi-topology learning settings using unified metrics that capture both predictive accuracy and physics-informed constraint violations. We additionally compare constraint-aware training objectives, including MSE, augmented Lagrangian, and violation-based Lagrangian losses, to characterize accuracy-robustness trade-offs across settings. Data processing, training, and evaluation frameworks are open-sourced as the LUMINA suite to support reproducibility and accelerate future research on feasibility-aware OPF surrogates.