PowerGraph: A power grid benchmark dataset for graph neural networks


METADATA ONLY
Loading...

Date

2023-12

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Public Graph Neural Networks (GNN) benchmark datasets facilitate the use of GNN and enhance GNN applicability to diverse disciplines. The community currently lacks public datasets of electrical power grids for GNN applications. Indeed, GNNs have the potential for capturing complex power grid phenomena over alternative machine learning techniques. Power grids are complex engineered networks that are naturally amenable to graph representations. Therefore, GNN have the potential for capturing the behaviour of power grids over alternative machine learning techniques. To this aim, we develop a graph dataset for cascading failure events, which are the major cause of blackouts in electric power grids. Historical blackout datasets are scarce and incomplete. The assessment of vulnerability and the identification of critical components are usually conducted via computationally expensive offline simulations of cascading failures. Instead, we propose the use of machine learning models for the online detection of cascading failures leveraging the knowledge of the system state at the onset of the cascade. We develop PowerGraph, a graph dataset modelling cascading failures in power grids, designed for two purposes, namely, i) training GNN models for different graph-level tasks including multi-class classification, binary classification, and regression, and ii) explaining GNN models. The dataset generated via physics-based cascading failure model ensures generality of the operating and environmental conditions by spanning diverse failure scenarios. In addition, we foster the use of the dataset to benchmark GNN explainability methods by assigning ground-truth edge-level explanations. PowerGraph helps the development of better GNN models for graph-level tasks and explainability, critical in many domains ranging from chemistry to biology, where the systems and processes can be described as graphs. The dataset is available at https://figshare.com/articles/dataset/PowerGraph/22820534 and the code at https://anonymous.4open.science/r/PowerGraph/.

Permanent link

Publication status

published

Editor

Book title

NeurIPS 2023 Workshop: New Frontiers in Graph Learning

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

New Frontiers in Graph Learning (GLFrontiers) Workshop @ NeurIPS 2023

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09452 - Sansavini, Giovanni / Sansavini, Giovanni check_circle
02219 - ETH AI Center / ETH AI Center
02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.

Notes

Funding

Related publications and datasets