Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions
Abstract
Solving the nonlinear AC optimal power flow (AC OPF) problem remains a major computational bottleneck for real-time grid operations. In this paper, we propose a residual learning paradigm that uses fast DC optimal power flow (DC OPF) solutions as a baseline, and learns only the nonlinear corrections required to provide the full AC-OPF solution. The method utilizes a topology-aware Graph Neural Network with local attention and two-level DC feature integration, trained using a physics-informed loss that enforces AC power-flow feasibility and operational limits. Evaluations on OPFData for 57-, 118-, and 2000-bus systems show around 25% lower MSE, up to 3X reduction in feasibility error, and up to 13X runtime speedup compared to conventional AC OPF solvers. The model maintains accuracy under N-1 contingencies and scales efficiently to large networks. These results demonstrate that residual learning is a practical and scalable bridge between linear approximations and AC-feasible OPF, enabling near real-time operational decision making.
Keywords
Cite
@article{arxiv.2510.16064,
title = {Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions},
author = {Muhy Eddin Za'ter and Bri-Mathias Hodge and Kyri Baker},
journal= {arXiv preprint arXiv:2510.16064},
year = {2025}
}