Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Changhun, Conrad, Timon, Karim, Redwanul, Oelhaf, Julian, Riebesel, David, Arias-Vergara, Tomás, Maier, Andreas, Jäger, Johann, Bayer, Siming
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914340044537856
author Kim, Changhun
Conrad, Timon
Karim, Redwanul
Oelhaf, Julian
Riebesel, David
Arias-Vergara, Tomás
Maier, Andreas
Jäger, Johann
Bayer, Siming
author_facet Kim, Changhun
Conrad, Timon
Karim, Redwanul
Oelhaf, Julian
Riebesel, David
Arias-Vergara, Tomás
Maier, Andreas
Jäger, Johann
Bayer, Siming
contents Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the soft constraint on the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases to form a fully differentiable knownoperator layer inside the computation graph, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4-32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08 deg in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2-5x faster batched inference than NR on 4-1024-bus grids.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22458
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
Kim, Changhun
Conrad, Timon
Karim, Redwanul
Oelhaf, Julian
Riebesel, David
Arias-Vergara, Tomás
Maier, Andreas
Jäger, Johann
Bayer, Siming
Machine Learning
Artificial Intelligence
Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the soft constraint on the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases to form a fully differentiable knownoperator layer inside the computation graph, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4-32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08 deg in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2-5x faster batched inference than NR on 4-1024-bus grids.
title Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.22458