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.
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
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.
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.
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.
Smart Images

Figure CN120262398A_ABST