Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pasini, Massimiliano Lupo, Li, Yijiang, Kim, Kibaek, Kuruganti, Teja
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918517989703680
author Pasini, Massimiliano Lupo
Li, Yijiang
Kim, Kibaek
Kuruganti, Teja
author_facet Pasini, Massimiliano Lupo
Li, Yijiang
Kim, Kibaek
Kuruganti, Teja
contents Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either flatten the native heterogeneous structure of power networks, target a limited set of grid topologies, or lack scalable infrastructure for graph foundation model (GFM) training. This paper presents a scalable heterogeneous graph neural network (GNN) workflow, built on HydraGNN, for data-driven OPF surrogate modeling and OPF-GFM development. The workflow preserves the distinct node and edge types of power grids -- buses, generators, loads, shunts, AC lines, transformers, and device-to-bus couplings -- and supports distributed preprocessing, training, hyperparameter optimization (HPO), and downstream fine-tuning on leadership-class supercomputers. Using three million heterogeneous graph instances spanning ten PGLib-OPF cases, from 14 to 13,659 buses, we conduct DeepHyper-driven HPO on the ORNL Frontier supercomputer. The campaign identifies compact models ($\sim$1.6--1.7M parameters) with the lowest validation losses. Downstream experiments on feasibility classification and N-1 contingency regression show that fine-tuning pretrained OPF GFM improves low-data accuracy, stabilizes training, accelerates convergence, and reduces adaptation cost when partial or head-only fine-tuning is used.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23194
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
Pasini, Massimiliano Lupo
Li, Yijiang
Kim, Kibaek
Kuruganti, Teja
Machine Learning
Artificial Intelligence
68T07, 68T09, 68T20
I.2.8; I.2.11
Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either flatten the native heterogeneous structure of power networks, target a limited set of grid topologies, or lack scalable infrastructure for graph foundation model (GFM) training. This paper presents a scalable heterogeneous graph neural network (GNN) workflow, built on HydraGNN, for data-driven OPF surrogate modeling and OPF-GFM development. The workflow preserves the distinct node and edge types of power grids -- buses, generators, loads, shunts, AC lines, transformers, and device-to-bus couplings -- and supports distributed preprocessing, training, hyperparameter optimization (HPO), and downstream fine-tuning on leadership-class supercomputers. Using three million heterogeneous graph instances spanning ten PGLib-OPF cases, from 14 to 13,659 buses, we conduct DeepHyper-driven HPO on the ORNL Frontier supercomputer. The campaign identifies compact models ($\sim$1.6--1.7M parameters) with the lowest validation losses. Downstream experiments on feasibility classification and N-1 contingency regression show that fine-tuning pretrained OPF GFM improves low-data accuracy, stabilizes training, accelerates convergence, and reduces adaptation cost when partial or head-only fine-tuning is used.
title Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
topic Machine Learning
Artificial Intelligence
68T07, 68T09, 68T20
I.2.8; I.2.11
url https://arxiv.org/abs/2605.23194