Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator

2025-09-26

AI Summary

Existing physics-informed graph neural networks (PIGNNs) suffer from degraded physical consistency and insufficient accuracy during inference for AC power flow solving. To address this, we propose a physics-consistency-enhanced PIGNN tailored for medium- and high-voltage power systems. Methodologically: (i) we design an edge-aware attention mechanism that explicitly incorporates line physical parameters via edge-specific biases; and (ii) we introduce a backtracking line-search correction operator to enforce the physical descent criterion during inference. Experiments across 4–1024-bus systems demonstrate that our method achieves a voltage magnitude RMSE of 0.00033 p.u. and a phase angle error of only 0.08°, improving accuracy by over 87% relative to baseline methods. Moreover, batch inference speed is 2–5× faster than the Newton–Raphson method, significantly enhancing both robustness and engineering practicality.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace classic Newton--Raphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases, capturing the grid's anisotropy, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4--32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08$^circ$ in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2--5$ imes$ faster batched inference than NR on 4--1024-bus grids.

Problem

• Improving accuracy of physics-informed GNNs for AC power flow
• Enhancing physics loss effectiveness during inference phase
• Developing faster alternative to Newton-Raphson power flow solvers

Innovation

• Edge-aware attention mechanism encoding line physics
• Backtracking line-search-based globalized correction operator
• Physics-informed GNN for fast AC power-flow solving