Metraipolis › archive › dc_c997acaf4604
Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference — arXiv:2610.21833
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21833
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:22:41.851Z
- SHA-256 of the archived text
27a5d3e80b731d5d61a8b403dccf57dc65f13c5a0ff94618df94c426b426da00- Stable URL of this page
https://metraipolis.com/documento/dc_c997acaf4604
How to cite
Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference — arXiv:2610.21833 — arXiv (en), https://arxiv.org/abs/2610.21833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c997acaf4604 (Metraipolis archive dc_c997acaf4604, sha256 27a5d3e80b731d5d61a8b403dccf57dc65f13c5a0ff94618df94c426b426da00)
BibTeX
@misc{dcc997acaf4604,
title = {Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference — arXiv:2610.21833},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21833},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c997acaf4604; sha256 27a5d3e80b731d5d61a8b403dccf57dc65f13c5a0ff94618df94c426b426da00},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Grid foundation models (GridFMs) are graph transformers pretrained on a masked power-flow objective, and evaluate power flow orders of magnitude faster than an iterative solver. Their size, however, targets data-centre inference, whereas low-inertia operation increasingly asks for inference at the edge, next to the measurement, at batch size one and within a single synchrophasor (PMU) reporting frame. We distil a 20.1M-parameter, 12-layer GridFM teacher into a 0.62M-parameter, 6-layer student, a $32.5\times$ parameter reduction at half the message-passing depth, using an objective that combines the masked power-flow loss with output, physics-residual, latent-state and attention transfer. The physics-residual term, which matches the teacher's power-residual profile, has not previously been applied to typed power-grid graphs. We evaluate on a renewable variant of the IEEE 118-bus benchmark grid in which 26 of the conventional (synchronous) generators are replaced by inverter-based renewables with battery flexibility and standardised reactive-power limits (IEEE 1547), giving $97\,529$ physically valid (AC-OPF-feasible) operating scenarios, and we ablate all eight combinations of the transfer terms, reporting accuracy against ground truth and fidelity to the teacher separately. Distillation lowers student error on all four predicted quantities, by up to $48\%$ on active-power dispatch, and every distilled student is more accurate than its teacher on reactive-power dispatch. The gain is largely carried by the output matching term. The physics-residual term, in the layer-aggregated form used here, is consistently harmful, which we attribute to the spatial averaging it applies to a bus-level residual field. The resulting student is $32.5\times$ smaller in parameter count and has half the message-passing depth, making it a candidate for subsequent edge-device benchmarking. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.21833 — 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 2026-10-16T08:48:02.758Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).