Electricity larceny detection method based on combination of user load and electricity utilization parameters

A detection method and electric parameter technology, applied in the field of electric stealing detection, can solve the problems of large number of users and low detection efficiency, and achieve the effects of improving accuracy, avoiding information loss, good recognition effect and practical application value

Active Publication Date: 2020-10-02
国网江西省电力有限公司供电服务管理中心 +2
View PDF10 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In electricity theft detection, there is still a large number of users, and the detection efficiency is not high.

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
  • Electricity larceny detection method based on combination of user load and electricity utilization parameters
  • Electricity larceny detection method based on combination of user load and electricity utilization parameters
  • Electricity larceny detection method based on combination of user load and electricity utilization parameters

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Provide a specific implementation example below to illustrate the method that the present invention realizes:

[0021] Such as figure 1 As shown, a method of electricity theft detection based on the combination of user load and electricity consumption parameters is as follows:

[0022] Select 439 users in a certain area, and export the data from the database. The experimental data is the user load data for a total of three months from April to June 2019. Since the data collection interval is 15 minutes, 96 load data are included in the daily record. The daily load data of these 439 users is preprocessed, and the typical daily load curve of each user is obtained by using the weighted average method for each user's load data, and the typical daily load curve of each user is used as clustering sample data.

[0023] Use fuzzy C-means algorithm and random selection method to classify users. Since the initial cluster center is randomly selected, the results may be different...

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 an electricity larceny detection method based on combination of user load and electricity utilization parameters. The method comprises steps of clustering the user load data byadopting a method of combining a fuzzy C-means algorithm and a random selection method, dividing users into different categories, finding out load characteristic curves of the users, calculating distances between daily load curves of the users and the characteristic load curves of the users, and finding out suspected abnormal users with relatively large deviation degrees; and finally, further observing and screening by utilizing the user electricity stealing identification model based on the electricity utilization parameters to find out the electricity stealing users. According to the invention, the user load and the power utilization parameters are combined; an electricity larceny preliminary screening model is esrablished based on a load curve; the improved parallel long short-term memory neural network LSTM algorithm is used for training, the time sequence and regularity of electric energy quality monitoring system data in an actual power grid are fully considered, a specific abnormal value can be accurately detected, a good recognition effect and an actual application value are achieved, and the accuracy of the algorithm is improved.

Description

technical field [0001] The invention relates to the technical field of electricity theft detection, in particular to an electricity theft detection method based on the combination of user load and electricity consumption parameters. Background technique [0002] The accuracy and quality reliability of electric energy measurement directly affect the economic interests of users and the utilization rate of social energy. Electricity theft refers to the illegal use of electric power resources. This practice seriously affects the accuracy of measurement, not only causes huge losses to electric power companies, but also seriously threatens the safe operation of the power grid. In the process of power grid development, the problem of stealing electricity has always existed, and it has shown a high-tech development trend, and it is more concealed. In electricity theft detection, there are still problems of large number of users and low detection efficiency. Contents of the invent...

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): G06K9/62G06N3/04G06Q50/06
CPCG06Q50/06G06N3/044G06N3/045G06F18/23213G06F18/2433
Inventor 邓高峰温和刘强王珺张春强胡涛赵震宇郑振洲郭雪薇刘仕萍李肖
Owner 国网江西省电力有限公司供电服务管理中心
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap