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

TL;DR

This paper introduces DDA-PIGCN, a novel physics-informed graph neural network that dynamically adapts domain knowledge and incorporates spatiotemporal features to improve AC-OPF solutions, achieving high accuracy and constraint satisfaction.

Contribution

The paper presents a new graph-based learning framework with dynamic domain adaptation and physics-informed constraints for AC-OPF, integrating spatiotemporal data and improving solution accuracy.

Findings

Achieves MAE from 0.0011 to 0.0624 on test cases.

Constraint satisfaction rates between 99.6% and 100%.

Outperforms existing AC-OPF methods in accuracy and reliability.

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.