A method and apparatus for topology adaptive power flow calculation based on physical information graph neural networks

By constructing a topology-adaptive power flow calculation method based on physical information graph neural networks and introducing multi-section and time-series data for training, the accuracy problem of power flow calculation under topology changes and new energy uncertainties is solved, and efficient and accurate power flow prediction is achieved.

CN122136865APending Publication Date: 2026-06-02CHINA SOUTHERN POWER GRID DIGITAL GRID GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA SOUTHERN POWER GRID DIGITAL GRID GRP CO LTD
Filing Date
2026-01-16
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing power flow calculation methods struggle to maintain high-precision predictions when faced with power system topology changes and uncertainties in new energy sources, and require a large amount of retraining data, making them unsuitable for adapting to rapid topology changes in real-world engineering projects.

Method used

A topology-adaptive power flow calculation method based on physical information graph neural networks is adopted. By constructing a graph structure with power grid bus nodes as graph nodes and topological relationships as edges, the model is trained by combining multi-section and multi-time series data. Physical constraints are introduced to reduce the dependence on power flow solution labels and improve the robustness and generalization ability of the model.

Benefits of technology

It can accurately and efficiently predict power flow distribution under complex operating conditions, enhance the model's ability to adapt to power grids of different sizes and topologies, reduce the need for power flow delabeling, and improve computation speed and prediction accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122136865A_ABST
    Figure CN122136865A_ABST
Patent Text Reader

Abstract

This application relates to a topology adaptive power flow calculation method, apparatus, computer device, computer-readable storage medium, and computer program product based on a physical information graph neural network. The method includes: constructing a graph structure corresponding to the target power grid, using different types of power grid bus nodes as graph nodes and the topological relationships between power grid bus nodes as edges of the graph nodes; inputting the graph structure corresponding to the target power grid into a pre-trained power flow calculation model, and outputting the power flow calculation results of the target power grid; wherein, the power flow calculation results include the voltage magnitude and voltage phase angle of all graph nodes in the graph structure; the power flow calculation results are calculated by the pre-trained power flow calculation model based on node characteristics and edge characteristics; the pre-trained power flow calculation model is trained using power grid graph structure samples under different operating conditions and / or different data acquisition times, as well as physical constraints. This method can improve the intelligence of power flow calculation.
Need to check novelty before this filing date? Find Prior Art