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

Abnormal electricity utilization user detection method based on semi-supervised learning

A semi-supervised learning and abnormal power consumption technology, applied in the field of detection, can solve the problem of model training without a training set, and achieve the effect of improving accuracy and efficiency

Inactive Publication Date: 2018-11-13
SHANDONG UNIV OF SCI & TECH
View PDF0 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in reality, the initial stage of data analysis and detection does not have a large training set for model training

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
  • Abnormal electricity utilization user detection method based on semi-supervised learning
  • Abnormal electricity utilization user detection method based on semi-supervised learning
  • Abnormal electricity utilization user detection method based on semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0041] 1. Model steps and framework

[0042] The inventive method realization work mainly comprises the following steps:

[0043] First, assuming that most people are normal users, and the behavior characteristics of normal users and abnormal (stealing power) users are different, use the cluster analysis method to screen out outlier users, that is, get the first-level gray list.

[0044] Secondly, based on the first-level gray list, calculate the outlier degree (LOF value) of the user, judge the user's suspicious degree according to the outlier degree, and form a second-level gray list with suspicious degree ranking.

[0045] The third step, based on the secondary gray list, go to the scene to collect fraudulent evidence of outlier users, obtain a blacklist, and store it in the blacklist database.

[0046] In the fourth step, in view of the fa...

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 an abnormal electricity utilization user detection method based on semi-supervised learning, belonging to the technical field of detection. The method comprises the following steps: data preprocessing; generation of a first grade grey list based on clustering analysis; generation of a second grade grey list based on outlier degree calculation; and generation of a third grade grey list based on similarity calculation. An abnormal electricity utilization user detection model based on semi-supervised learning in the invention aims at forming a user dubiety degree ordered list, thus a key detection list is provided for manual detection, and accuracy and efficiency of on-site detection are improved.

Description

technical field [0001] The invention belongs to the technical field of detection, and in particular relates to a method for detecting abnormal electricity users based on semi-supervised learning. Background technique [0002] According to research, the operating losses caused by non-technical problems in my country's power system are as high as tens of billions of dollars every year. Non-technical losses refer to operational losses caused by a series of false power consumption behaviors such as power theft and fraud by power users on the distribution network side. With the continuous advancement of the smart grid and the rapid development of sensor acquisition technology, the power load data of power companies has increased massively, which makes it more and more difficult to detect abnormal power users. [0003] In recent years, some intelligent detection algorithms have been proposed to overcome the disadvantages of high blindness and low accuracy of original manual detec...

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
IPC IPC(8): G06Q50/06G06K9/62
CPCG06Q50/06G06F18/23G06F18/22G06F18/2433
Inventor 纪淑娟周金萍李凯旋张纯金
Owner SHANDONG UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com