PF$\Delta$: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations

TL;DR

PFΔ is a comprehensive benchmark dataset for power flow calculations that captures diverse real-world scenarios, aiding the development and evaluation of faster, more accurate methods including machine learning approaches.

Contribution

The paper introduces PFΔ, a large-scale dataset with nearly 860,000 instances covering various system sizes, contingencies, and near-infeasible cases, facilitating systematic benchmarking of power flow solutions.

Findings

Traditional solvers and GNN-based methods face challenges on the dataset.

The dataset reveals specific scenarios where existing methods struggle.

Open problems for improving power flow computation are identified.

Abstract

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 PF$\Delta$, a benchmark dataset for power flow that captures diverse variations in load, generation, and topology. PF$\Delta$ 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.