PowerGraph
PowerGraph is a multifaceted GNN dataset for diverse tasks that includes power flow and fault scenarios with real-world explanations, providing a valuable resource for developing improved GNN models for node-level, graph-level tasks and explainability methods in power system modeling.

PowerGraph comprises GNN-tailored datasets for i. power flows, ii. optimal power flows, and iii. cascading failure analyses of power grids. We provide ground-truth explanations for the cascading failure analysis. PowerGraph datasets benchmark GNN methods for node-level and graph-level tasks and explainability.

Available Leaderboards
Graph Binary Classification Graph Multiclass Classification Graph Regression Node OPF Node PF

Leaderboard: Graph Binary Classification

Leaderboard: Graph Multiclass Classification

Leaderboard: Graph Regression

Leaderboard: Node Optimal Powerflow

Leaderboard: Node Powerflow

Citation

Consider citing our paper if you use PowerGraph datasets, if you want to reference our leaderboards or if you use the method rankings or our evaluation protocol: 
@article{varbella2024powergraph,
    title={PowerGraph: A power grid benchmark dataset for graph neural networks},
    author={Varbella, Anna and Amara, Kenza and El-Assady, Mennatallah and Gjorgiev, Blazhe and Sansavini, Giovanni},
    journal={arXiv preprint arXiv:2402.02827},
    year={2024}
}

Maintainers