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

TL;DR

The paper tackles the challenge of deep learning-based power flow analysis under topology and scale variations. It introduces SaMPFA, which combines Local Topology Slicing for diverse cross-scale training with a Reference-free Multi-task Graph Learning model that predicts bus and branch powers directly, plus BFS-based angle recovery for phase information. A data-physics hybrid loss enforces KCL, branch loss, and angle patterns to ensure physical consistency, improving real-world reliability. Experiments on the IEEE 39-bus system and a real provincial grid show strong cross-scale generalization and significantly faster NR convergence when initialized with RMGL-based predictions, highlighting SaMPFA's practical potential for scalable online power flow analysis.

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.

Figures (14)

• Figure 1: Distributions of graph characteristics under different bus counts.
• Figure 2: Per-unit admittance distribution of branches in a real-world power system.
• Figure 3: Framework of SaMPFA.
• Figure 4: Structure of RMGL.
• Figure 5: Local topology slicing.