Metraipolis › archive › dc_4fd4313d6edf

Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints — arXiv:2610.38985

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38985
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:00.470Z
SHA-256 of the archived text
50dbf707f38c104f982a9c381e944d0f3cc6af70d9c12fd18751f0e6ef22c13b
Stable URL of this page
https://metraipolis.com/documento/dc_4fd4313d6edf

How to cite

Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints — arXiv:2610.38985 — arXiv (en), https://arxiv.org/abs/2610.38985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fd4313d6edf (Metraipolis archive dc_4fd4313d6edf, sha256 50dbf707f38c104f982a9c381e944d0f3cc6af70d9c12fd18751f0e6ef22c13b)
BibTeX
@misc{dc4fd4313d6edf,
  title = {Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints — arXiv:2610.38985},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38985},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fd4313d6edf; sha256 50dbf707f38c104f982a9c381e944d0f3cc6af70d9c12fd18751f0e6ef22c13b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fast and accurate models for AC power flow (ACPF) are increasingly important as modern electrical grids require more frequent system analyses. Graph neural networks (GNNs) naturally exploit electrical grid topology, yet the effects of architectural design choices on predictive performance remain poorly understood given differences in graph representations and evaluation settings across studies. We present a unified benchmark of representative GNN architectures for ACPF prediction under a common experimental framework. All models use identical preprocessing and training procedures and comparable parameter budgets, isolating the impact of message-passing mechanisms and inductive biases. We also analyze errors by distance from the slack bus and systematically ablate key design components. We evaluate predictive accuracy and physical consistency on the IEEE 14-bus and IEEE 118-bus systems. Results indicate that anisotropic message-passing architectures offer the most favorable trade-off between predictive accuracy and physical consistency under the studied parameter and topology constraints. Explicit edge features encoding line impedances and global context aggregation are particularly important for representing electrical interactions and system-wide dependencies, especially for voltage-angle predictions on the topologically bottlenecked IEEE-118 grid. Under a budget with approximately fixed parameters, two or three message-passing layers generally provide the best balance between depth and representation width, while additional depth offers no consistent improvement. Ablations also show that standard residual and root connections are not necessarily beneficial in shallow models, and that aggregation operators involve trade-offs between statistical accuracy and physical consistency. These results provide practical guidelines for designing graph-based power system models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.38985 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:08.686Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).