Method and device for optimizing the equipment utilization rate of power distribution network

The invention discloses a method and device for optimizing the equipment utilization rate of a power distribution network, and the method comprises the steps: building an LSTM autoencoder through training, carrying out the feature extraction of a daily load curve set of the power distribution network, obtaining a deep feature load sequence of the power distribution network, and achieving the dimension reduction of a high-dimensional load curve; and then clustering the deep characteristic load sequences by using an improved fuzzy C-means clustering algorithm to achieve accurate classification of load characteristics of various power consumers, and establishing a power distribution network equipment utilization rate optimization model taking the maximum equipment utilization rate and the maximum user satisfaction as targets and considering the classification load time-sharing demand response based on a load sequence classification result. The method and device can accurately guide usersto use electricity in an