Paper Overview
Field: ML Authors: Alban Puech, Matteo Mazzonelli, Tamara R. Govindasamy arXiv: 2508.03802
Summary
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. The authors 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, they introduce the open-source GridFM Development Framework, which standardizes synthetic data generation and training in a low-code environment. They also release large-scale datasets containing millions of PF and OPF scenarios across diverse grid topologies to support reproducible benchmarking.
Results
GENCO was evaluated on the PFDelta and OPFData benchmarks against state-of-the-art neural solvers and classical solvers (including Newton-Raphson and IPOPT), and on real Hydro-Québec SCADA data:
- Power Flow: For large-scale PF, GENCO recovers the full AC operating state, 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 runs at roughly 2x DC-PF runtime.
- Optimal Power Flow: GENCO is 85x faster than IPOPT while outperforming DC-OPF on feasibility, optimality, and runtime.
- State Estimation: GENCO is more robust than classical weighted least squares (WLS) to noisy measurements and network parameter errors, consistently returning high-quality estimates even when WLS fails to converge.
---
*Auto-collected on 2026-08-12*