Unsupervised clustering method and device for power system operating conditions

Abstract

The invention provides an unsupervised clustering method and device for power system operating conditions, wherein the method comprises the following steps: obtaining power system power flow cross sections to be analyzed at different times, and constructing power flow vectors corresponding to each power flow cross section, wherein all power flow vectors constitute power flow vector spaces; using at-distribution random nearest neighbor embedding algorithm for data dimensionality reduction in the power flow vector space; using a hierarchical clustering algorithm for clustering analysis of the reduced dimension power flow vector space to obtain the clustering result of the operation conditions of the power system to be analyzed. In the clustering analysis of power system operating conditions, in addition to considering trend information, power network topology information is also used, the t-distribution stochastic nearest neighbor embedding algorithm is utilized to reduce the dimensionof power flow vector can effectively reduce the computational complexity while preserving the local structure of the original data. The hierarchical clustering algorithm is utilized to cluster the reduced dimension power flow vector can perform better in dealing with the complex distribution of samples.

Description

Technical field [0001] The present invention relates to the technical field, and more specifically, to a method and device for unsupervised clustering of power system operating conditions. Background technique [0002] The operation mode of the power system refers to the overall technical plan for guiding the production and operation of the power system prepared by the power system dispatching department. The typical steps to determine the operation mode of a transmission grid mainly include: determining the grid structure, mainly considering the planning of high-voltage transmission lines, transformers and large-scale units in the regional grid, referring to the maintenance plan, and also considering the connection to the adjacent grid The operation of the transmission line; the predicted load level, the load of each node of the transmission network refers to the sum of the load borne by the node. The load of the transmission network considers four typical modes: large in winte...

AI Technical Summary

Problems solved by technology

If only the load level and power generation output of the system are used for cluster analysis, the network topology information of the power system will be lost; in addition, the k-Means clustering algorithm does not perform well when dealing with complex distributions, and is not suitable for the existing complex power grid operation mode Analysis

Images