Dynamic Domain Adaptation-Driven Physics-Informed Graph Representation Learning for AC-OPF

2025-05-31

AI Summary

To address weak constraint modeling capability and difficulty in integrating spatiotemporal knowledge in AC optimal power flow (AC-OPF) solving, this paper proposes a physics-informed graph neural network framework incorporating physical laws and dynamic domain adaptation. Methodologically: (1) a dynamic domain adaptation mechanism iteratively calibrates the distribution of state variables; (2) multi-layer hard physical constraint consistency optimization ensures solution feasibility; and (3) a power-grid topology-driven spatiotemporal graph representation learning module explicitly models spatiotemporal dependencies. The key innovation lies in the first integration of dynamic domain adaptation and hard-constraint regularization into a physics-informed graph convolutional network (PI-GCN) architecture. Evaluated on IEEE 9-, 30-, and 300-bus systems, the method achieves MAEs of 0.0011–0.0624 and constraint satisfaction rates of 99.6%–100%, significantly outperforming existing data-driven approaches.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Alternating Current Optimal Power Flow (AC-OPF) aims to optimize generator power outputs by utilizing the non-linear relationships between voltage magnitudes and phase angles in a power system. However, current AC-OPF solvers struggle to effectively represent the complex relationship between variable distributions in the constraint space and their corresponding optimal solutions. This limitation in constraint modeling restricts the system's ability to develop diverse knowledge representations. Additionally, modeling the power grid solely based on spatial topology further limits the integration of additional prior knowledge, such as temporal information. To overcome these challenges, we propose DDA-PIGCN (Dynamic Domain Adaptation-Driven Physics-Informed Graph Convolutional Network), a new method designed to address constraint-related issues and build a graph-based learning framework that incorporates spatiotemporal features. DDA-PIGCN improves consistency optimization for features with varying long-range dependencies by applying multi-layer, hard physics-informed constraints. It also uses a dynamic domain adaptation learning mechanism that iteratively updates and refines key state variables under predefined constraints, enabling precise constraint verification. Moreover, it captures spatiotemporal dependencies between generators and loads by leveraging the physical structure of the power grid, allowing for deep integration of topological information across time and space. Extensive comparative and ablation studies show that DDA-PIGCN delivers strong performance across several IEEE standard test cases (such as case9, case30, and case300), achieving mean absolute errors (MAE) from 0.0011 to 0.0624 and constraint satisfaction rates between 99.6% and 100%, establishing it as a reliable and efficient AC-OPF solver.

Problem

• Improves constraint modeling for AC-OPF solutions
• Integrates spatiotemporal features in power grid modeling
• Enhances consistency optimization with physics-informed constraints

Innovation

• Dynamic domain adaptation learning mechanism
• Physics-informed graph convolutional network
• Spatiotemporal feature integration framework