Graph data modeling electric power fingerprint identification method of electrical equipment, storage medium and system

Abstract

The invention provides a graph data modeling electric power fingerprint identification method of electrical equipment, a storage medium and a system. The method comprises the steps of detecting an input event of the electrical equipment at a power utilization bus in real time, and extracting a plurality of electrical operation features of the input electrical equipment, establishing an association relationship between every two electrical operation characteristics according to a mutual information entropy theory, taking the extracted electrical operation characteristics as nodes, taking an association relationship between every two electrical operation characteristics as edges, and generating electric fingerprint graph data containing the nodes and the edges according to a graph theory, and performing graph representation learning on the electric power fingerprint graph data by using a graph convolutional network, and constructing a mapping relationship between the electric power fingerprint graph data and the electrical equipment to realize load identification. The mapping relation does not need to be determined through a large amount of calculation in the load identification process, and the electrical operation characteristics of the electrical equipment can be directly obtained based on the electric fingerprint graph data, so that the non-intrusive load identification algorithm is simple, the identification speed is high, and the operation efficiency is high.

Description

technical field [0001] The present invention relates to the field of information communication technology, and in particular to a method, storage medium and system for electrical equipment image data modeling power fingerprint identification. Background technique [0002] The Ubiquitous Power Internet of Things is an important development direction of the current smart grid. Its main role is to promote user-interactive smart power consumption and tap the incremental value of power consumption big data, and how to obtain fine-grained information on power consumption by users is one of them. points and difficulties. The advanced measurement system can realize the analysis and monitoring of users' electricity consumption information, especially the load identification, which helps to realize the two-way information interaction between users and the power grid. [0003] Non-invasive load monitoring (non-intrusive load monitoring, NILM) was first proposed by Professor Hart in th...

AI Technical Summary

Problems solved by technology

Although the above methods have achieved good results, due to the lack of a good mapping relationship between the electrical equipment and the electrical operating characteristic data of the electrical equipment, it usually takes a lot of calculations to determine the mapping relationship in the load identification process, resulting in a complex algorithm structure. Moreover, in the process of data processing, the above methods need to input the electrical operation characteristics of electrical equipment into the non-intrusive load identification algorithm in order to realize load identification, resulting in slow identification speed and low operating efficiency of the non-intrusive load identification algorithm.

Images