Medium-voltage power distribution network equipment load state identification method

Abstract

The invention discloses a medium-voltage power distribution network equipment load state identification method. The method comprises the following steps: S1, selecting state characteristics for representing the load state of to-be-identified equipment; S2, acquiring power consumption data of the to-be-identified equipment at the identification measurement point, and performing feature extraction to obtain a multi-dimensional feature sequence; S3, respectively performing difference calculation on the state features and each extracted feature sequence to obtain a differentiated feature sequence, respectively calculating correlation coefficients between every two of the differentiated feature sequences, and screening out a required feature sequence; S4, remapping the screened feature sequences into a two-dimensional multi-channel matrix; S5, performing model training on the two-dimensional multi-channel matrix by using a deep convolutional neural network to obtain a prediction model; and S6, identifying the real-time load state of the equipment to be identified by using the prediction model. According to the invention, equipment load state identification can be realized only by a small number of training samples, and the method has the advantages of simple implementation method, high identification precision and efficiency and the like.

Description

technical field [0001] The invention relates to the technical field of medium-voltage distribution network equipment monitoring, in particular to a method for identifying the load status of medium-voltage distribution network equipment. Background technique [0002] Non-intrusive load monitoring (NILM) refers to the installation of measuring equipment at the user's electricity entrance to collect power data such as voltage, current, frequency, and power, and decompose it into the power consumption status of independent equipment. The method of information such as power consumption. According to the user's electricity consumption behavior information obtained by load monitoring, it can provide a basis for the power grid company's dispatching, demand response and other advanced electricity consumption strategies, and can also provide a reference for users to formulate a reasonable electricity consumption plan. [0003] Non-intrusive load monitoring (NILM) is a key component i...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is that: aiming at the technical problems existing in the prior art, the present invention provides a method for identifying the load status of medium-voltage distribution network equipment with simple implementation, high identification accuracy and high efficiency, and only requires a small amount of training Samples can be used to identify equipment load status, which solves the problem of excessive dimensionality of traditional identification methods

Images