OPF-HGNN: Generalizable Heterogeneous Graph Neural Networks for AC Optimal Power Flow

Salah Ghamizi*, Aoxiang Ma, Jun Cao, Pedro Rodriguez Cortes

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The precise solution of the Alternating Current Optimal Power Flow (AC-OPF) problem is a pivotal challenge in the domain of real-time electricity grid operations. This problem is notorious for its significant computational complexity, primarily attributable to its inherently nonlinear and nonconvex nature. Recently, there has been a growing interest in harnessing Graph Neural Networks (GNN) as a means to tackle this optimization task, leveraging the incorporation of grid topology within neural network models. Nonetheless, existing techniques fall short in accommodating the diverse array of components found in contemporary grid networks and restrict their scope to homogeneous graphs. Furthermore, the constraints imposed by the grid networks are often overlooked, resulting in suboptimal or even infeasible solutions. To address the generalization and effectiveness of existing end-to-end OPF learning solutions, we propose OPF-HGNN, a new graph neural network (GNN) architecture and training framework that leverages heterogeneous graph neural networks and incorporates the grid constraints in the node loss function using differentiable penalty regularization. We demonstrate that OPF-HGNN is robust and outperforms traditional GNN learning by two orders of magnitude traditional GNN learning across a large variety of real-world grid topologies and generalization settings.

Original languageEnglish
Title of host publication2024 IEEE Power and Energy Society General Meeting, PESGM 2024
PublisherIEEE Computer Society
ISBN (Electronic)9798350381832
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event2024 IEEE Power and Energy Society General Meeting, PESGM 2024 - Seattle, United States
Duration: 21 Jul 202425 Jul 2024

Publication series

NameIEEE Power and Energy Society General Meeting
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Conference

Conference2024 IEEE Power and Energy Society General Meeting, PESGM 2024
Country/TerritoryUnited States
CitySeattle
Period21/07/2425/07/24

Keywords

  • Graph Neural Network
  • Heterogeneous GNN
  • OPF
  • Physics-Informed
  • Robustness

Fingerprint

Dive into the research topics of 'OPF-HGNN: Generalizable Heterogeneous Graph Neural Networks for AC Optimal Power Flow'. Together they form a unique fingerprint.

Cite this