Paper Overview
Field: ML Authors: Alban Puech, Matteo Mazzonelli, Tamara R. Govindasamy Published: 2026-08-11 arXiv: 2508.03802
Abstract
Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis, where strict physical consistency must be enforced. We present GENCO (GEometric Neural Corrective Optimizer), a unified neural solver for steady-state transmission grid analysis that handles power flow (PF), optimal power flow (OPF), and state estimation (SE) within a single architecture and shared network representation.
To support advances in neural power system solvers, we introduce the open-source GridFM Development Framework, which standardizes synthetic data generation and training in a low-code environment. We also release large-scale datasets with millions of PF and OPF scenarios across diverse grid topologies to support reproducible benchmarking.
Key Results
We evaluate GENCO on the PFDelta and OPFData benchmarks against state-of-the-art neural solvers and classical solvers, including Newton-Raphson and IPOPT, and test it on real Hydro-Québec SCADA data.
- Power Flow: For large-scale PF, GENCO recovers full AC operating states, including voltage magnitudes and reactive power that DC-PF cannot provide, while matching DC-PF-level active power balance residuals. It is 30x faster than Newton-Raphson and only 2x the runtime of DC-PF.
- Optimal Power Flow: GENCO is 85x faster than IPOPT while outperforming DC-OPF in feasibility, optimality, and runtime.
- State Estimation: GENCO is more robust than classical weighted least squares to noisy measurements and network parameter errors, consistently returning high-quality estimates even when weighted least squares fails to converge.
--- *Auto-collected on 2026-08-12*