Transformer area multilayer topological structure identification method based on data driving

Abstract

The invention discloses a transformer area multi-layer topological structure identification method based on data driving, and the method comprises the steps: S1, converting the identification problem of a multi-layer topological structure into the solution of an adjacent matrix in a graph theory according to the characteristic that a low-voltage distribution network presents a radial tree structure; s2, performing frequency domain filtering on the active power time sequence of the feeder unit and the branch unit for feature extraction; s3, obtaining the upstream and downstream and parallel relation of the units by adopting a correlation analysis method based on the highlighted features; s4, in combination with the voltage amplitude characteristics of the nodes, realizing identification of adjacent units of the user, and determining the corresponding relation between the user and the isolated sub-network; and S5, carrying out linear transformation on the line section of the isolated sub-network and the active power sequence of the user while considering the data error, and determining the line section to which the user belongs through regression analysis to achieve the construction of a multi-layer topological structure. According to the method, the identification of a feeder-branch-phase line-user multilayer topological structure is realized, so that the investment for deploying a large number of monitoring equipment or changing an equipment communication mode is greatly reduced.

Description

technical field [0001] The invention relates to the data-driven technical field of power distribution systems, in particular to a data-driven multi-layer topology identification method for a station area. Background technique [0002] As the "last mile" of power supply service, low-voltage distribution network (abbreviated as station area) is an important link to ensure power quality. In recent years, smart meters have been widely used and deeply promoted in Taiwan areas, further improving the service quality of smart grids. Accurate topology is the basis for low-voltage distribution network to carry out application functions such as line loss analysis, power outage management, cost control, and three-phase unbalance control. However, in the actual operation scenario, due to problems such as chaotic connections and incomplete archives, the accuracy of the "feeder-branch-phase-line-user" relationship in the marketing topology archives of some station areas is low, requiring ...

AI Technical Summary

Problems solved by technology

To perform topology identification based on carrier communication technology, the user meter communication module needs to be replaced. Although this method is easy to implement and has a high recognition rate, it requires both the concentrator and the smart meter to have carrier communication functions, and is susceptible to load fluctuations and interference from noise sources.

Among the data-driven algorithms, although most of them realize the identification of "phase line-user" or "feeder-user" relationship, because the upstream, downstream and parallel relationship of branch nodes are not considered, it is impossible to determine the section to which the user belongs , that is, it is impossible to build a multi-layer topology in the platform area

Images