PF∆: A Benchmark Dataset for Power Flow With Load, Generator, & Topology Variations

Abstract

Large-scale renewable energy integration and climate-induced extreme weather events increase uncertainty in power system operations, calling for tools that can accurately and efficiently simulate a wide range of scenarios and operating conditions. Machine learning approaches offer a potential speedup over traditional solvers, but their performance has not been systematically assessed on benchmarks that capture real-world variability. This paper introduces PF∆, a benchmark dataset designed to evaluate power flow methods under variations in load, generation, and topology. We evaluate traditional and graph neural network-based approaches, and demonstrate key areas for improvement in existing methods. All data and model implementations are available in the code repository and the data archive.

Download

• Paper
• Summary Slides
• Poster

Citation

Bhagavathula, A., Carbonero, A., Rivera, A., & Donti, P. (2025). PF∆: A Benchmark Dataset for Power Flow With Load, Generator, & Topology Variations. In ICLR 2025 Workshop on Tackling Climate Change with Machine Learning.

@inproceedings{bhagavathula2025pf,
  title={PF∆: A Benchmark Dataset for Power Flow With Load, Generator, & Topology Variations},
  author={Bhagavathula, Anvita and Carbonero, Alvaro and Rivera, Ana and Donti, Priya},
  booktitle={ICLR 2025 Workshop on Tackling Climate Change with Machine Learning},
  url={https://www.climatechange.ai/papers/iclr2025/67},
  year={2025}
}