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

Automatic electricity stealing identification method based on data mining technology

A technology of data mining and identification methods, which is applied in the field of electric stealing identification, can solve problems such as low intelligence, lack of deep mining of electric power data, and long promotion cycle, so as to improve extraction efficiency, improve machine learning effect, and improve identification accuracy. Effect

Pending Publication Date: 2021-09-17
国网吉林省电力有限公司营销服务中心
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the identification technology in the prior art must be matched with customized hardware equipment, the cost is high, the promotion cycle is long, and it is impossible to break through the limitations of expert algorithms, lack of deep mining of original power data, and intelligent Due to the shortcomings of low degree of automation, an automatic electricity stealing identification method based on data mining technology is proposed

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
  • Automatic electricity stealing identification method based on data mining technology
  • Automatic electricity stealing identification method based on data mining technology
  • Automatic electricity stealing identification method based on data mining technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] refer to Figure 1-4 , a kind of automatic electric stealing identification method based on data mining technology, comprises the following steps:

[0048] S1: Obtain files and power consumption data;

[0049] S2: Data preprocessing: Data preprocessing handles the missing values, 0 values ​​and obvious wrong data in the daily frozen display of the user's electric energy meter;

[0050] S2: Data preprocessing: first, intercept the data during the periods of abnormal fluctuations in power consumption of users who have been investigated and dealt with, and second, reverse the data according to the time series;

[0051] S4: Build a feature recognition model for electricity stealing behavior. The model is built using: first, time-segmented method to build a feature engineering model, and second, correlation analysis;

[0052] S5: Use supervised machine learning model, training model;

[0053] S6: Model validation and optimization.

[0054] In this embodiment, S2 specifical...

Embodiment 2

[0078] In this example, figure 1 It is the daily power consumption change curve of a power stealing user for 15 days before and after the date of investigation. Electricity, there should be abnormal fluctuations corresponding to the obvious decline in daily electricity consumption.

[0079] In this example, for figure 1 The power consumption change curve in is processed according to time reversal, and the abnormal fluctuation curve of power consumption shows a downward trend, simulating the power consumption behavior of power-stealing users, such as figure 2 shown; right figure 2 In the curve construction feature engineering, the data feature extraction of the curve fluctuation is carried out, the daily power change trend of the electricity-stealing users is summarized, and the electricity consumption behavior of the electricity-stealing users is further analyzed.

[0080] In this embodiment, based on the deficiencies in the existing power stealing analysis technology fie...

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 belongs to the technical field of electricity larceny identification, and particularly relates to an automatic electricity larceny identification method based on a data mining technology. The method aims to the problems that in the prior art, an identification technology must be matched with customized hardware equipment, the cost is high, the popularization period is long, the limitation of an expert algorithm cannot be broken through, and deep mining of original power data is lacked, and the intelligent degree is low. The invention provides the following scheme: the method comprises the following steps: S1: obtaining archive and electricity consumption data; s2, pretreating the data; s3, determining an object, to be specific, firstly, intercepting data of an electricity consumption abnormal fluctuation period of an investigated electricity stealing user, secondly, inverting the data according to a time sequence; S4, constructing an electricity stealing behavior feature recognition model; S5, using a supervised machine to learn a model and training the model. According to the method, the feature engineering is constructed for the electricity consumption data by adopting a segmentation method, and the model is trained through a supervised machine learning method, so that the recognition accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of electric stealing identification, in particular to an automatic electric stealing identification method based on data mining technology. Background technique [0002] At present, the identification of power-stealing users of public transformers and special transformers mainly relies on the experience accumulation and business knowledge of electricity inspectors. Regular or non-scheduled on-site inspections are efficient, low-cost, and low in intelligence. At the same time, electricity stealing technology presents a development trend of diversification, high technology, and strong concealment, and the limitations of anti-electricity stealing based on expert experience are becoming increasingly obvious. [0003] At this stage, the types and frequency of electricity consumption data collection are limited. In terms of intelligent analysis of electricity theft, it is still necessary to equip special acquisiti...

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): G06K9/62G06N20/10
CPCG06N20/10G06F18/241G06F18/214
Inventor 唐伟宁都明亮吴刚孔凡强鞠默欣
Owner 国网吉林省电力有限公司营销服务中心
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