Data-driven anti-electricity stealing intelligent early warning method

A data-driven, anti-stealing technology, applied in the field of electric power industry, can solve the problems of low accuracy of investigation and punishment of electricity theft, insufficient data mining depth, lack of digital handles, etc., to reduce personnel operation and inspection costs, and improve investigation rate , The effect of reducing operating costs

Active Publication Date: 2022-07-12
国网新疆电力有限公司营销服务中心 +3
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Strengthen the in-depth research and application of data, promote the deep integration of big data and artificial intelligence technology and anti-theft investigation and violation business, and solve the lack of digital grasp in the existing anti-theft investigation and violation work, insufficient data mining depth, low accuracy of electricity theft investigation and punishment, Cases with less intelligence

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
  • Data-driven anti-electricity stealing intelligent early warning method
  • Data-driven anti-electricity stealing intelligent early warning method
  • Data-driven anti-electricity stealing intelligent early warning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Step 1: Extract the internal data of the power grid, plus the imported external big data, preprocess the user data, extract the features such as maximum power, power consumption, compliance rate and other characteristics to establish a user power consumption feature set, and then use a random search strategy And the wrapping algorithm, perform feature subset search, compare various search results, select the data with the best measurement performance, and construct the key feature set of user electricity consumption;

[0037] Step 2: Use the traditional industry classification method to preliminarily classify the training data, and build the must-connect constraint set ML and the non-connection constraint set CL according to the nature difference between the major industries. , voltage, current, maximum power, peak-to-valley ratio, and other key features of user electricity consumption, as well as user classification information obtained by using traditional industry cla...

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 data-driven anti-electricity-stealing intelligent early-warning method, which utilizes artificial intelligence technologies such as data mining and machine learning to construct a data-driven anti-electricity-stealing intelligent early-warning model, performs hierarchical early-warning on abnormal electricity consumption behaviors, and realizes electricity-stealing early warning , Accurately locate users of electricity stealing, and continue to iteratively optimize the model and sample library to achieve continuous improvement of the accuracy of electricity stealing early warning. The workload of front-line employees improves the work efficiency of electric power enterprise personnel, reduces personnel operation and inspection costs, reduces operating costs, and greatly increases the rate of investigation and punishment of electricity theft.

Description

technical field [0001] The invention belongs to the field of the electric power industry, and in particular relates to a data-driven anti-electricity-stealing intelligent early-warning method. Background technique [0002] At present, electricity is a commodity. The promulgation of my country's Electricity Law has clarified the rights and obligations of both sides of the electricity supply and consumption, and has made the electricity market go on the road of standardization and legalization. Users must pay electricity fees on time according to the electricity price approved by the state and the records of the metering device. Electricity theft is an illegal and criminal act, and any unit or individual is prohibited from illegally occupying and using electric energy. However, in real life, some enterprises and individuals are driven by the idea of ​​illegal profit to steal electricity in order to achieve the purpose of paying less or even no electricity fee, and the state a...

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): G06Q50/06G06K9/62
CPCG06Q50/06G06F18/23213G06F18/24Y02E40/70
Inventor 张银昌陈杰马迅谢智刘晨
Owner 国网新疆电力有限公司营销服务中心
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