Newest papers

Benchmarking CPU, GPU, and ML Power-Flow Solvers from 14 to 70,000 Buses

Benjamin Donnot, Sami Tazi, Eva Boguslawski, Nourredine Henka · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27930 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los surrogados de batader aprendidos para el cálculo de flujo de energía (PF) generalmente están motivados por la velocidad, en comparación con una única base de CPU. Mostramos que esta comparación es frágil: a través de 7 solventes basados en CPU de código abierto evaluados en entradas idénticas, el rendimiento varía en aproximadamente 2,5-3 órdenes de magnitud, por lo que la elección de la base solo puede dar la vuelta a la conclusión. Construimos un punto de referencia que abarca 9 solventes basados en física: 7 basados en CPU y 2 basados en GPU, incluyendo un nuevo solvente de GPU basado en espacio, gumsim2grid - y 3 surrogados de ML publicados, evaluados bajo una comprobación compartida, independientemente implementada de KCL-mismatch en 15 redes de 14

Machine translation (Meta M2M100); the English original follows.

Abstract

Learned surrogates for power-flow (PF) computation are usually motivated by speed, compared against a single CPU-based baseline. We show this comparison is fragile: across 7 open-source CPU-based solvers evaluated on identical inputs, throughput varies by roughly 2.5-3 orders of magnitude, so the choice of baseline alone can flip the conclusion. We build a benchmark spanning 9 physics-based solvers: 7 CPU-based and 2 GPU-based, including a new batched GPU solver, gumsim2grid - and 3 published ML surrogates, evaluated under a shared, independently implemented KCL-mismatch check across 15 grids from 14 to 70,000 buses. On the PF task itself, a sufficiently parallelized CPU solver or gpusim2grid matches or exceeds the throughput of the ML surrogates we test while remaining orders of magnitude more accurate; we find no evidence that these GNN-style surrogates are yet competitive for PF specifically, though prior work reports genuine gains on related but more combinatorial tasks such as optimal power flow or power grid control. Beyond this finding, we hope the benchmark suite, code and reference evaluator released at https://github.com/Grid2op/gpusim2grid helps close a broader reproducibility gap in this space, where batched GPU-based PF solvers are rarely open-sourced or evaluated against a common set of baselines.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmarking, Benchmark (surveying), Computer science, Solver, Parallel computing, Set (abstract data type)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange