A user energy consumption behavior identification method for a distribution network containing distributed energy sources

Abstract

The application discloses a kind of user energy consumption behavior identification methods containing distributed energy distribution network, it is related to user energy consumption behavior identification field, the method includes the following steps: data is collected from the bus of distribution network, and data is randomly divided into training set and test set;For training set, it is identified by classification, for the flexible load that is greatly influenced by weather and / or season, further period identification is carried out;Training set data is imported into GRU neural network and is trained, and test set is used to verify the identification effect of training model on test set during training process;Load operation curve is input into training model and is identified by classification, and the identification result of the energy consumption behavior of distribution network user is obtained.The application can provide effective monitoring and identification means for the load energy consumption state of distribution network user by deep mining of distribution network bus sampling data, is favorable for improving the efficiency and accuracy of distribution network energy consumption identification, and has important significance for the development of low-voltage distribution network demand response and the like.

Images