← Back to all news
arXiv Machine Learning By Vlad Alexandru S\u{a}nduleac, Shahariya Rasheed Rayamarakkarveettil Puthanpurayil, Noman Khan, Remus Teodorescu

Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference

Read the original on arXiv Machine Learning →

The paper presents a physics‑aware distillation of a large Grid Foundation Model (GridFM) for real‑time edge inference. A 20.1 M‑parameter, 12‑layer teacher is compressed into a 0.62 M‑parameter, 6‑layer student, achieving a 32.5× reduction in parameters and halving message‑passing depth while improving accuracy on active‑power dispatch by up to 48 % and always outperforming the teacher on reactive‑power dispatch. The distillation objective combines masked power‑flow loss with output, physics‑residual, latent‑state, and attention transfer, though the physics‑residual term proved detrimental in this setting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 11

GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis

arXiv:2608. 09921v1 Announce Type: new Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis, where strict physical consistency must be enforced.

By Alban Puech, Matteo Mazzonelli, Tamara R. Govindasamy, Mangaliso Mngomezulu, H\'ector Maeso-Garc\'ia, Thomas Tolhurst, Javad Bayazi, Ali Moeini, Naomi Simumba, Celia Cintas, David Nelischer, Romeo Kienzler, Jonas Weiss, Anna Varbella, Florian D\"orfler, Gabriela Hug, Martin Mevissen, Juan Bernab\'e-Moreno, Fran\c{c}ois Mirall\`es, Hendrik F. Hamann, Etienne Vos, Thomas Brunschwiler
benchmarks
More like this →
arXiv AI
Sep 28

Hierarchical GNNs for power flow: letting physics shape the hierarchy

The paper presents a hierarchical graph neural network (GNN) approach for power‑flow modeling that leverages physics‑informed graph reductions. By exchanging information through two reduced graphs within the corrective network of GENCO, the model achieves superior generalization across three grid topologies and new operating scenarios, outperforming both the flat baseline and a Quotient construction. Training required only about 200 epochs and fewer than 1,900 scenarios per grid, yet the hierarchical models achieved a macro family‑balanced voltage error of 0.851±0.110, a 51.3% improvement over the per‑bus mean fitted on training solutions.

By Carmine Delle Femine, Leire Garin Atxaga, Asier Diaz-Iglesias, Juan Pablo Maroto Herrera, Ane Miren Florez-Tapia, Marco Quartulli, Izaro Goienetxea Urziku
More like this →