Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A non-invasive electrical appliance identification method based on boost model

A non-invasive, identification method technology, applied in the field of non-invasive electrical appliance identification based on the Boost model, can solve the problems of large model errors, difficult implementation, and unsuitable for comprehensive promotion.

Active Publication Date: 2022-02-22
无锡英臻科技股份有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Intrusively, sensors with digital communication functions are installed at the interface between each electrical appliance and the grid to monitor the operating status and power consumption of each electrical appliance. The advantage of this method is that the measurement is accurate, but the disadvantage is that it needs To install circuit facilities on electrical appliances, the installation work needs to enter the interior of the electrical appliances, which is difficult to implement and will affect normal production work. In the method, the model identified by the rated power has a large error, and often requires the reactive power data of the meter, while the model recognized by the instantaneous current change has too high a requirement for the sampling rate of the meter

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
  • A non-invasive electrical appliance identification method based on boost model
  • A non-invasive electrical appliance identification method based on boost model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0028] like figure 1 Shown, the technical scheme that the present invention adopts is:

[0029] A non-invasive electrical appliance identification method based on Boost model, comprising the following steps:

[0030] Step 1: Use unlabeled data collection to collect the data of the electric meter, judge the time point of the sudden change of the power value in real time, and store the data in a short period of time before and after. The unlabeled data refers to the power of the electrical appliance obtained from the electric meter data.

[0031] Step 2: Enter the user training stage, guide the user to switch on and off the electrical appliances that need to be identified, and record the data in the short period of time before and after the power mutation event of the meter in the corresponding period and the corresponding electrical applian...

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 discloses a non-intrusive electrical appliance identification method based on the Boost model, which comprises the following steps: 1. collecting data from electric meters by adopting unlabeled data collection; , and record the power data of the meter and the corresponding electrical label; 3. First, use the Bootstrap algorithm to expand the labeled set, and combine it with the unlabeled set to form a training set, and then use it to establish a classification model; 4. Collect power mutation events in real time, use the training A good model classifies it and displays the identified electrical consumer results to the user; 5. Add the new sample and new label in the pre-identification stage to the original labeled data set, and repeat steps 3 and 4; 6. Use a model that meets the accuracy requirements to identify electrical appliances, and feed back to users or demanders in real time; the invention can realize the identification of electrical appliances among residential users through the power data of the total electric meter and a small amount of training data.

Description

technical field [0001] The invention relates to the technical field of online electrical appliance identification, in particular to a non-invasive electrical appliance identification method based on a Boost model. Background technique [0002] Power load monitoring refers to the technology of collecting electrical parameters generated during load operation through smart meters, and then analyzing its operating status. For home users, load monitoring can enable users to know the time-sharing power, start and stop time of each type of electrical appliances, and guide electricity consumption behavior based on this information, so as to achieve the purpose of energy saving. For power companies, through the monitoring of household electricity consumption, a typical user data platform is established to carry out fine modeling, analysis, classification, and formulation of power consumption behaviors of different users, so as to realize the rational allocation of power resources. ...

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 Patents(China)
IPC IPC(8): G06K9/62G06Q50/06
CPCG06Q50/06G06F18/2148G06F18/24
Inventor 王椭
Owner 无锡英臻科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products