PFΔ: A Benchmark Dataset for Power Flow

Anvita Bhagavathula – MIT

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. 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. To tackle this challenge, we introduces PFΔ, a benchmark dataset for power flow that captures diverse variations in load, generation, and topology. PFΔ contains 859,800 solved PF instances spanning six bus system sizes, capturing three contingency scenarios (N , N -1, N -2), and including close-to-infeasible cases near steady-state voltage stability limits. We evaluate traditional solvers and GNN-based methods, highlight areas where existing approaches struggle, and identify open problems for future research.