The doi above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/b27152e4-4237-40f9-a72c-e6a1ca916960

Lin, Nan; Orfanoudakis, Stavros (2024): Data underlying the publication: PowerFlowNet: Leveraging Message Passing GNNs for Improved Power Flow Approximation. Version 1. 4TU.ResearchData. dataset. https://doi.org/10.4121/b27152e4-4237-40f9-a72c-e6a1ca916960.v1

Dataset

• Electrical and Electronic Engineering
• Engineering

power flow, power system, smart grid

CC BY 4.0

RefWorks, BibTeX, Reference Manager, Endnote, DataCite, NLM, DC, CFF

by Nan Lin , Stavros Orfanoudakis

Synthetic power flow dataset consist of three cases: 14-bus, 118-bus and 6470-bus. The line parameters, generator/load injections, voltage setpoints are randomly sampled based on the standard scenario. The 14-bus case consists of 100000 scenarios, 118-bus 50000 scenarios, and 6470-bus 30000 scenarios.

If you use parts of this dataset, please cite as:

@misc{lin2023powerflownet,

   title={PowerFlowNet: Leveraging Message Passing GNNs for Improved Power Flow Approximation}, 

   author={Nan Lin and Stavros Orfanoudakis and Nathan Ordonez Cardenas and Juan S. Giraldo and Pedro P. Vergara},

   year={2023},

   eprint={2311.03415},

   archivePrefix={arXiv},

   primaryClass={cs.LG}

}

• 2024-02-05 first online, published, posted

4TU.ResearchData

numpy arrays

PowerFlowNet: Leveraging Message Passing GNNs for Improved Power Flow Approximation

• https://arxiv.org/abs/2311.03415

TU Delft, Faculty of Electrical Engineering, Mathematics, and Computer Science, Department of Electrical Sustainable Energy, Intelligent Electrical Power Grids Section