A Distribution Network Topology Identification Method Based on XGBoost
By using the XGBoost-based distribution network topology identification method and the state change data of sectionalizing switches and tie switches, a high-precision topology identification model is constructed, which solves the problem of inaccurate topology identification in existing technologies and improves the identification efficiency and security of distribution networks.
CN117093934BActive Publication Date: 2026-07-17NANJING INST OF TECH
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING INST OF TECH
- Filing Date
- 2023-08-16
- Publication Date
- 2026-07-17
Smart Images
Figure CN117093934B_ABST
Abstract
This invention discloses a distribution network topology identification method based on XGBoost, comprising: acquiring the existing distribution network topology; synchronously mixing data from the beginning, end, and users of the lines according to time series to obtain load data; merging load data with the same topology in the distribution network with its corresponding topology to form a topology identification dataset for that topology; establishing the distribution network topology identification dataset; training and testing the XGBoost model using the topology identification dataset; and inputting the line data requiring topology prediction into the tested XGBoost-based distribution network topology identification prediction model. This invention has the advantages of wide applicability and high identification accuracy, enabling distribution network topology identification and solving the problems of complex distribution network structures and untimely topology updates. It provides guidance and reference for business scenarios such as distribution network topology maintenance.
Need to check novelty before this filing date? Find Prior Art