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

2025-10-16

AI Summary

To address the low computational efficiency of nonlinear AC optimal power flow (AC OPF) in real-time power system operation, this paper proposes a residual-correction graph neural network (GNN) method. Starting from a fast yet simplified DC OPF solution as an initial baseline, we design a topology-aware GNN architecture that integrates dual-layer DC features and local self-attention, coupled with a physics-informed loss function explicitly enforcing AC power flow feasibility and operational constraints. Our key contribution lies in embedding residual learning into the power system optimization pipeline. Extensive evaluations on multiple standard test systems demonstrate a ~25% reduction in mean squared error (MSE), up to a threefold decrease in feasibility violation, and up to 13× speedup over traditional solvers. Moreover, the method maintains high accuracy and strong generalization under N−1 contingency scenarios and exhibits favorable scalability.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Solving nonlinear AC optimal power flow computational bottleneck
• Learning residual corrections from DC to AC solutions
• Enabling near real-time grid operations with scalability

Innovation

• Residual learning corrects DC OPF with nonlinear adjustments
• Graph Neural Network integrates topology and DC features
• Physics-informed loss ensures feasibility and operational limits