Scale-Adaptive Power Flow Analysis with Local Topology Slicing and Multi-Task Graph Learning

2026-01-04

arXiv.org

AI Summary

This work addresses the limited generalization of power flow analysis methods across varying network scales and topologies by proposing the SaMPFA framework. SaMPFA enhances cross-scale modeling through Local Topology Slice (LTS) sampling and introduces a Reference-free Multi-task Graph Learning (RMGL) architecture that directly predicts nodal voltages and branch power flows, thereby circumventing error accumulation inherent in conventional phase-angle-based prediction pathways. Physical laws are explicitly embedded as constraints to ensure prediction consistency with underlying power system physics. Experimental results demonstrate significant performance gains, achieving accuracy improvements of 4.47% on the IEEE 39-bus system and 36.82% on a real-world provincial power grid in China, underscoring the model’s enhanced robustness and cross-scale generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Multiagent Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Developing deep learning models with strong adaptability to topological variations is of great practical significance for power flow analysis. To enhance model performance under variable system scales and improve robustness in branch power prediction, this paper proposes a Scale-adaptive Multi-task Power Flow Analysis (SaMPFA) framework. SaMPFA introduces a Local Topology Slicing (LTS) sampling technique that extracts subgraphs of different scales from the complete power network to strengthen the model's cross-scale learning capability. Furthermore, a Reference-free Multi-task Graph Learning (RMGL) model is designed for robust power flow prediction. Unlike existing approaches, RMGL predicts bus voltages and branch powers instead of phase angles. This design not only avoids the risk of error amplification in branch power calculation but also guides the model to learn the physical relationships of phase angle differences. In addition, the loss function incorporates extra terms that encourage the model to capture the physical patterns of angle differences and power transmission, further improving consistency between predictions and physical laws. Simulations on the IEEE 39-bus system and a real provincial grid in China demonstrate that the proposed model achieves superior adaptability and generalization under variable system scales, with accuracy improvements of 4.47% and 36.82%, respectively.

Problem

• power flow analysis
• topological variations
• system scale adaptability
• branch power prediction
• graph learning

Innovation

• Local Topology Slicing
• Multi-task Graph Learning
• Scale-Adaptive Power Flow
• Reference-free Prediction
• Physics-Informed Loss