Unlock instant, AI-driven research and patent intelligence for your innovation.

Risk user identification method based on measurement data multi-situation judgment

A technology for user identification and data measurement, applied in data processing applications, character and pattern recognition, instruments, etc., it can solve the problems of hidden electricity stealing, inability to change the count of electricity meters, and inability to trace back, etc., to achieve the effect of improving the accuracy rate

Pending Publication Date: 2020-11-13
STATE GRID ZHEJIANG ELECTRIC POWER CO LTD SHAOXING POWER SUPPLY CO +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] (3) Install a meter with anti-stealing function in the home of a user with a record of stealing electricity. This type of meter cannot change its original count and cannot be traced back
[0016] (1) The method of stealing electricity is more high-tech and requires certain technical content;
[0017] (2) The way of stealing electricity is more concealed;
[0018] (3) Electricity stealers often need to have specialized knowledge and skills

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
  • Risk user identification method based on measurement data multi-situation judgment
  • Risk user identification method based on measurement data multi-situation judgment
  • Risk user identification method based on measurement data multi-situation judgment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Specifically, such as figure 1 As shown, the risk user identification method includes:

[0057] 11. Obtain the user's electricity consumption data, and preprocess the user's electricity consumption data to obtain mature electricity consumption data;

[0058] 12. Extract characteristic parameters from mature electricity consumption data as the input feature set of SVM algorithm,

[0059] 13. Convert the input feature set into a feature vector, and send the feature vector into the SVM classifier for classification training;

[0060] 14. Identify risky users based on the trained SVM algorithm combined with characteristic parameters.

[0061] In implementation, the extraction of characteristic parameters from mature power consumption data as the input feature set of the SVM algorithm includes: selecting active power P, reactive power Q, load utilization rate index μ, daily maximum load, and power fluctuation as data The category extracts characteristic parameters from ma...

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 a risk user identification method based on measurement data multi-situation evaluation, and the method comprises the steps: obtaining user power utilization data, and carrying out the preprocessing of the user power utilization data to obtain mature power utilization data; extracting feature parameters from the mature electricity consumption data to serve as an input featureset of an SVM algorithm, converting the input feature set into feature vectors, and sending the feature vectors into an SVM classifier to be subjected to classification training; and identifying therisk user based on the trained SVM algorithm in combination with the feature parameters. Compared with a statistical index judgment method, the SVM classification algorithm used for identifying risk users or normal users is better improved, and the accuracy is obviously improved.

Description

technical field [0001] The application belongs to the field of power supply evaluation, and in particular relates to a risk user identification method based on multi-situation evaluation of measurement data. Background technique [0002] The energy loss of the power system can be divided into two categories: technical loss (Technical Loss, TL) and non-technical loss (Non-technical Loss, NTL). Among them, the technical loss includes the energy loss that is difficult to eliminate in the process of power transmission, power distribution and power transformation, mainly including the loss caused by the transmission of electric energy through the transmission line, the loss of the transformer and the loss of other equipment. Non-technical losses mainly refer to the losses caused by electricity stealing behaviors of power users, and power users who may have electricity stealing behaviors are called risk users. [0003] Technical losses and non-technical losses can be expressed by...

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): G06Q10/06G06Q50/06G06K9/62
CPCG06Q10/0635G06Q50/06G06F18/2411
Inventor 章剑光王锋华章坚民林海峰张磊张永建陈浩凌玲李晓彤田雁宁胡利辉周晟张旭阳韩保礼
Owner STATE GRID ZHEJIANG ELECTRIC POWER CO LTD SHAOXING POWER SUPPLY CO