Supercharge Your Innovation With Domain-Expert AI Agents!

House non-intrusive load intelligent identification method based on data mining

A non-intrusive and intelligent identification technology, applied in the field of power system, can solve the problems of not conforming to the intelligent construction of power grid, unfavorable promotion, high installation cost, etc., and achieve the effect of promoting application, improving safety performance and reducing labor cost

Pending Publication Date: 2021-07-30
清科优能(深圳)技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the installation cost of this method is high, which is not conducive to popularization
At the same time, the installation of a large number of sensors on the user side will have varying degrees of impact on normal power consumption, which does not meet the requirements of intelligent grid construction

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • House non-intrusive load intelligent identification method based on data mining
  • House non-intrusive load intelligent identification method based on data mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A non-intrusive load intelligent identification method for buildings based on data mining, see figure 1 , including the following steps:

[0042] S1: Obtain the historical electrical quantity data of each equipment, and construct the load characteristic database of each equipment, including:

[0043] Extract the characteristic quantities in the historical electrical quantity data of each equipment respectively, and construct the load characteristic database of each equipment; wherein, the category of the characteristic quantity in the load characteristic database includes the following one or a combination of several data: rated active power, rated reactive power Power, current harmonic content, fundamental current RMS and current total harmonic distortion.

[0044] Specifically, assume that the historical electrical quantity data sequence of a device is D={d 1 , d 2 ,...,d N}, where N is the data length, d i (1≤i≤N) is the i-th historical electrical quantity data,...

Embodiment 2

[0058] Embodiment 2 On the basis of Embodiment 1, a device type identification method is defined.

[0059] see figure 2 , when it is detected that the electrical quantity data to be identified that is overloaded meets the preset mutation condition, compare the electrical quantity data to be identified in the detection sequence with the load feature database of each device, and calculate the similarity of the electrical quantity data to be identified Specifically include:

[0060] S31: When detecting overloaded electrical quantity data to be identified, judge whether the electrical quantity data to be identified satisfies the mutation condition, if yes, perform step S32, specifically including:

[0061] Traverse the active power of the electrical quantity data to be identified in the detection sequence point by point, and calculate the difference between the active powers of two adjacent electrical quantity data to be identified; when the difference is greater than the preset...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a house non-intrusive load intelligent identification method based on data mining, and belongs to the technical field of electric power; the method comprises the following steps: obtaining historical electrical quantity data of each device, and constructing a load feature library of each device; acquiring to-be-identified electrical quantity data, and constructing a detection sequence; detecting the to-be-identified electrical quantity data in the detection sequence in sequence; when it is detected that the overload to-be-identified electrical quantity data meets a preset sudden change condition, comparing the to-be-identified electrical quantity data in the detection sequence with the load feature library of each device, and calculating the similarity of the to-be-identified electrical quantity data; and obtaining the equipment type of the equipment corresponding to the detection sequence according to the similarity of all the to-be-identified electrical quantity data in the detection sequence. According to the method, the installation cost is reduced, and the recognition precision is improved.

Description

technical field [0001] The invention belongs to the technical field of power systems, and in particular relates to a data mining-based non-intrusive intelligent load identification method for buildings. Background technique [0002] Power user load monitoring is the primary link to realize intelligent power consumption. The load monitoring technology monitors the detailed operating status of each electrical appliance in the user by sampling and analyzing the total load data of the user, so as to obtain the electric energy of each electrical appliance of the power user. Data information such as consumption and electricity consumption behavior. In the past, power user monitoring mainly collected total load data for metering. If the monitoring of the operating status of each user's electrical equipment can be realized, the access status of illegal electrical appliances can be found in time, and the safety of electricity consumption can be improved. has more significance. [0...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q50/06G06K9/62H02J3/00
CPCG06Q10/0635G06Q50/06H02J3/00H02J2310/70H02J2203/20H02J2203/10G06F18/22
Inventor 周少雄沈国安汪大明
Owner 清科优能(深圳)技术有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com