Power distribution network user load characteristic classification method based on use and acquisition data

The invention relates to a power distribution network user load characteristic classification method based on use and acquisition data, and the method comprises the steps: 1, building an original user load characteristic database through user data collected by a use and acquisition system, carrying out the normalization processing of the data, and unifying the data in a rough numerical interval; 2, performing feature extraction on the original user load feature database by using a US-ELM algorithm, screening out load features having the most representative row for user load features, and constructing a user load feature set; 3, introducing an improved FCM algorithm to perform clustering analysis on the user load feature set, taking the low-dimensional data after dimension reduction in the step 2 as the input of the improved FCM algorithm, and clustering the user load feature set into a class C; and 4, performing category division on the original user load data by using a result obtained by clustering, and per