Substation characteristic analysis method based on multi-element clustering model and two-stage clustering correction algorithm

The invention discloses a substation characteristic analysis method based on a multi-element clustering model and a two-stage clustering correction algorithm. Clustering analysis is an important method for extracting substation characteristics from a lot of load data, but substation loads include various user loads, the characteristics of the substation loads are very complex, if a single daily load curve or a user composition ratio is selected as an index for clustering, other factors can be ignored, and therefore the clustering result is not comprehensive. Thus, the substation characteristicanalysis method based on the multi-element clustering model and the two-stage clustering correction algorithm is provided. Firstly, the daily load curve data is clustered by means of a K-means algorithm, then the two-stage clustering correction algorithm is employed for correcting the clustering result of the daily load curve according to the substation user composition data. The research resultshows that the clustering