EnerGNN (Energy Graph Neural Network) is a GNN framework designed for real life energy networks.
The core package energnn includes:
- A complex graph data representation (in the form of Hyper Heterogeneous Multi Graphs),
- A library of compatible GNN models,
- A clear interface to apply them to your own real-life problems.
Companion packages are here to help you get started:
- pypowsybl-to-energnn helps you convert power systems files into the energnn data format,
- energnn-feature-store implements a feature store and a model registry, all displayed in a web interface,
- Install the core package:
pip install energnn. - Follow the tutorials in our documentation.
- Convert your own power system files with pypowsybl-to-energnn and start experimenting.
Our documentation is available at https://energnn.readthedocs.io/en/latest/.
Contributions of all kinds are welcome — code, documentation, issues, and reviews. To get involved:
- Read our Governance to understand how the project is organized and how decisions are made.
- Follow our Code of Conduct in all project spaces.
- Check the current committers and the process to become one, described in the governance document.
The Technical Steering Committee meets on the first Wednesday of each month at 10am CET. Meetings are open to everyone, published on the LFX calendar, and meeting notes are posted publicly.
- Balthazar Donon (Chair), RTE
- Hugo Kulesza, RTE
- Geoffroy Jamgotchian, RTE
- Steve Nouatin, RTE & DataStorm
- Louis Wehenkel, ULiège
| RTE | Université de Liège | INRIA |
|---|---|---|
@software{energnn,
author = {{Committers of EnerGNN}},
title = {{EnerGNN: A Graph Neural Network library for real-life Energy networks.}},
url = {https://github.com/energnn},
}