# PFDelta: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations

arXiv: https://arxiv.org/abs/2510.22048 · HTML: https://mlsanity.com/paper/2510.22048/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [The Power Grid Library for Benchmarking AC Optimal Power Flow Algorithms](https://mlsanity.com/paper/1908.02788/) (2019)
- [PowerModels.jl: An Open-Source Framework for Exploring Power Flow Formulations](https://mlsanity.com/paper/1711.01728/) (2017)
- [Learning to Solve the AC-OPF using Sensitivity-Informed Deep Neural Networks](https://mlsanity.com/paper/2103.14779/) (2021)
- [PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networks](https://mlsanity.com/paper/2311.03415/) (2023)
- [Power Flow Balancing with Decentralized Graph Neural Networks](https://mlsanity.com/paper/2111.02169/) (2021)
- [PowerGraph: A power grid benchmark dataset for graph neural networks](https://mlsanity.com/paper/2402.02827/) (2024)
- [Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids](https://mlsanity.com/paper/2109.03604/) (2021)
- [OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets](https://mlsanity.com/paper/2111.01228/) (2021)
- [PowRL: A Reinforcement Learning Framework for Robust Management of Power Networks](https://mlsanity.com/paper/2212.02397/) (2022)
- [AC Power Flow Data in MATPOWER and QCQP Format: iTesla, RTE Snapshots, and PEGASE](https://mlsanity.com/paper/1603.01533/) (2016)

## Built on by (most cited first, 7 of 7)

- [GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis](https://mlsanity.com/paper/2608.09921/) (2026)
- [Newton's Lantern: A Reinforcement Learning Framework for Finetuning AC Power Flow Warm Start Models](https://mlsanity.com/paper/2605.11102/) (2026)
- [Generating adversarial inputs for a graph neural network model of AC power flow](https://mlsanity.com/paper/2602.17975/) (2026)
- [Navigating the Safety-Fidelity Trade-off: Massive-Variate Time Series Forecasting for Power Systems via Probabilistic Scenarios](https://mlsanity.com/paper/2606.13338/) (2026)
- [Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems](https://mlsanity.com/paper/2609.33120/) (2026)
- [Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery](https://mlsanity.com/paper/2610.03872/) (2026)
- [Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model](https://mlsanity.com/paper/2610.20462/) (2026)

## Abstract (arXiv)

Power flow (PF) calculations are the backbone of real-time grid operations, across workflows such as contingency analysis (where repeated PF evaluations assess grid security under outages) and topology optimization (which involves PF-based searches over combinatorially large action spaces). Running these calculations at operational timescales or across large evaluation spaces remains a major computational bottleneck. Additionally, growing uncertainty in power system operations from the integration of renewables and climate-induced extreme weather also calls for tools that can accurately and efficiently simulate a wide range of scenarios and operating conditions. Machine learning methods 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 PFDelta, a benchmark dataset for power flow that captures diverse variations in load, generation, and topology. PFDelta contains 859,800 solved power flow instances spanning six different bus system sizes, capturing three types of contingency scenarios (N , N -1, and N -2), and including close-to-infeasible cases near steady-state voltage stability limits. We evaluate traditional solvers and GNN-based methods, highlighting key areas where existing approaches struggle, and identifying open problems for future research. Our dataset is available at https://huggingface.co/datasets/pfdelta/pfdelta/tree/main and our code with data generation scripts and model implementations is at https://github.com/MOSSLab-MIT/pfdelta.