Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions

2025/10/17 by Za'ter, Muhy Eddin, Hodge, Bri-Mathias, Baker, Kyri
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2510.16064

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.

Citations

• Deep learning for model correction of dynamical systems with data scarcity
• Improving the Accuracy of DC Optimal Power Flow Formulations via Parameter Optimization
• OPFData: Large-scale datasets for AC optimal power flow with topological perturbations
• CANOS: A Fast and Scalable Neural AC-OPF Solver Robust To N-1 Perturbations
• Applications of Physics-Informed Neural Networks in Power Systems - A Review
• Recent Developments in Security-Constrained AC Optimal Power Flow: Overview of Challenge 1 in the ARPA-E Grid Optimization Competition
• Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutions
• Leveraging power grid topology in machine learning assisted optimal power flow
• Learning to Optimize: A Primer and A Benchmark
• Optimal Power Flow Using Graph Neural Networks
• A Survey of Optimization Methods from a Machine Learning Perspective
• Learning Warm-Start Points for AC Optimal Power Flow
• A General Economic Dispatch Problem with Marginal Losses
• PowerModels.jl: An Open-Source Framework for Exploring Power Flow\n Formulations
• Deep Residual Learning for Image Recognition
• On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming

Cited by

• Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids

Related

• Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee
• Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow
• Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutions
• Initial estimate of AC optimal power flow with graph neural networks
• Improving the Accuracy of DC Optimal Power Flow Formulations via Parameter Optimization