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

2026-05-22 · Massimiliano Lupo Pasini, Yijiang Li, Kibaek Kim, Teja Kuruganti arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.23194

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter Optimization Graph Neural Network

Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

2026-05-14 · Ling Wang, Xin Liu, Songnan Liu, Jianan Wang 외 arxiv

Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding …

Billion-Scale Graph Foundation Models

2026-02-04 · Maya Bechler-Speicher, Yoel Gottlieb, Andrey Isakov, David Abensur 외 arxiv

Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining and lightweight adaptation, extending this paradigm to general, real-wo…

Graph Learning

Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval

2025-10-13 · Nilima Rao, Jagriti Srivastava, Pradeep Kumar Sharma, Hritvik Shrivastava arxiv

Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often f…

Semantic Similarity

HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction

2025-11-13 · Yueran Zhao, Zhang Zhang, Chao Sun, Tianze Wang 외 arxiv

Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participat…

RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation

2025-09-03 · Renzhi Wu, Junjie Yang, Li Chen, Hong Li 외 arxiv

Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGraph, a scalable graph learning framework …

Recommendation Systems Graph Neural Network Contrastive Learning Graph Learning