Metraipolis › archive › dc_7e10ac790ea3

GridSFM: A Foundation Model for Solving AC Optimal Power Flow — arXiv:2609.30173

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.30173
License (as archived): CC0-1.0
Archived: 2026-10-08T05:30:02.668Z
SHA-256 of the archived text: 446a00407477ac5f00dbc3f23b15369319c6b79d8101c3378f0b2a134bef7672
Stable URL of this page: https://metraipolis.com/documento/dc_7e10ac790ea3

How to cite

GridSFM: A Foundation Model for Solving AC Optimal Power Flow — arXiv:2609.30173 — arXiv (en), https://arxiv.org/abs/2609.30173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e10ac790ea3 (Metraipolis archive dc_7e10ac790ea3, sha256 446a00407477ac5f00dbc3f23b15369319c6b79d8101c3378f0b2a134bef7672)

BibTeX

@misc{dc7e10ac790ea3,
  title = {GridSFM: A Foundation Model for Solving AC Optimal Power Flow — arXiv:2609.30173},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30173},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e10ac790ea3; sha256 446a00407477ac5f00dbc3f23b15369319c6b79d8101c3378f0b2a134bef7672},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce GridSFM, a framework that combines a pretrained foundation model across grid topologies with physics-informed fine-tuning for solving AC Optimal Power Flow (AC-OPF) at scale. It is a $15$ million parameter physics-inspired graph neural network pretrained across $54$ topologies of $500$ to $4{,}000$ buses. Our model attains a $2.45\%$ zero-shot generation-cost error on a $10{,}000$ bus case held-out operating conditions with no degradation as system size grows. Building on this, we pair the pretrained backbone with a physics-informed fine-tuning design based on Newton's method for power flow. With only $100$ solved instances, GridSFM adapts to unseen grids up to $10{,}000$ buses. We show it out performs single topology, dedicated neural network models that are trained more data, both in terms of cost and solver iterations when deployed as warm starting points. In designing this foundation model, we overcome the fact that the feasible set for AC-OPF can be disconnected. This is an obstruction that prevents any continuous neural network from approximating the solution map. To do so, we lift the problem and relax its constraints with logarithmically penalized slacks. We prove that the resulting elastic feasible set is contractible, that the AC-OPF minimizers remain minimizers of the elastic problem above an explicit penalty threshold, and that projecting an approximate solution back onto the AC-OPF feasible set is well posed. We release all models, data, and code so that the community can build on a shared starting point for AC-OPF.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG).
Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.30173 — 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 2026-10-08T04:50:39.785Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).