Non-intrusive power load detection method and device and computer equipment

By obtaining the total active power and total reactive power time series, judging the turnover event, and using the K-Means++ algorithm and the Hippo optimization algorithm for load decomposition, the problem of privacy protection in non-invasive load monitoring is solved, and efficient and accurate identification and decomposition of electricity usage rules of electricity equipment is achieved.

CN120262398APending Publication Date: 2025-07-04STATE GRID CHONGQING ELECTRIC POWER COMPANY MARKETING SERVICE CENTER
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510543321.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-28
Publication Date
2025-07-04

AI Technical Summary

Technical Problem

The existing non-invasive load monitoring scheme requires the load data of the user's various power equipment to achieve load identification and decomposition, which violates the original intention of protecting user privacy.

Method used

By obtaining the total active power and total reactive power time series, judging the turnover event, constructing characteristic points of the load change amount, using K-Means++ algorithm clustering, combining intelligent optimization algorithms such as the Hippo optimization algorithm for load decomposition, identifying and decomposing the power consumption status of power-using equipment.

Benefits of technology

It realizes efficiently and accurately identify and decompose the electricity usage rules of electrical equipment without infringing on user privacy, reduces costs and is easy to implement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120262398A_ABST
    Figure CN120262398A_ABST
Patent Text Reader

Abstract

The invention relates to a non-intrusive power load detection method, a non-intrusive power load detection device and computer equipment. The method comprises the following steps: acquiring a total active power time sequence and a total reactive power time sequence of a to-be-detected power consumption main body in a set detection time period; judging whether a switching event occurs at the corresponding moment or not; if it is judged that the switching event occurs at the corresponding moment, the corresponding total active power variable quantity and total reactive power variable quantity when the switching event occurs are obtained to form load variable quantity feature points; clustering the load variation feature points corresponding to each switching event to obtain a load feature library of the to-be-detected power consumption main body; and carrying out load decomposition by adopting an intelligent optimization algorithm so as to obtain the use conditions of all kinds of electric equipment at all moments in the set detection time period. According to the method, the electric equipment can be divided into a plurality of classes, the electricity utilization rule of each class of electric equipment is analyzed and detected, and meanwhile, the privacy of a user is protected.
Need to check novelty before this filing date? Find Prior Art