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

Poor user identification method based on daily differential electricity consumption

A user identification and power consumption technology, applied in character and pattern recognition, data processing applications, instruments, etc., can solve the difficulties in the effectiveness analysis of differences in power consumption characteristics of different users, classification errors of user groups, and interpretation and verification of classification results To achieve the effect of enhancing adaptability and generalization ability, strong discrimination ability, and clear electricity consumption behavior

Pending Publication Date: 2021-01-08
STATE GRID ZHEJIANG ELECTRIC POWER CO LTD JINHUA POWER SUPPLY CO +2
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, scholars at home and abroad identify the types of user groups through the characteristics of users' electricity consumption, but most of them directly conduct cluster analysis on users based on electricity consumption data to study the characteristics of users' electricity consumption. There are two problems in this method. On the one hand, the number of clustering types is often determined artificially, which leads to difficulties in interpreting and verifying the classification results, and cannot intuitively analyze the effectiveness of the differences in power consumption characteristics of different users
On the other hand, researchers often directly define user group types subjectively based on clustering results, resulting in large errors in the classification of user groups.

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
  • Poor user identification method based on daily differential electricity consumption
  • Poor user identification method based on daily differential electricity consumption
  • Poor user identification method based on daily differential electricity consumption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0049] The present invention comprises the following steps:

[0050] 1) Obtain the user's daily power consumption data;

[0051] 2) Preprocess the daily electricity consumption data, eliminate users whose incomplete electricity data is greater than 30% of the annual electricity data, and use linear interpolation of adjacent non-missing values ​​for users whose incomplete electricity data is less than 30% of the annual electricity data For data completion, users who have duplicate data use time arrangement to remove duplicate data;

[0052] 3) Input the processed data into the trained classification model based on the Gini coefficient decision tree;

[0053] 4) The classification model identifies poor users based on daily electricity consumption data;

[0054] 5) Spot check the identification results, check the identification of th...

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 poor user identification method based on daily differential electricity consumption, and relates to a poor user identification method. At present, a user group type is subjectively defined often directly according to a clustering result, so that a relatively large error exists in user group classification. The method comprises the steps: firstly, carrying out poor user statistics on an investigated user group in a questionnaire mode, then dividing the investigated user group into a training sample group and a test sample group, and meanwhile, carrying out daily electricity consumption difference calculation on users of the training sample group to obtain the daily difference electricity consumption data; and respectively extracting electricity utilization characteristic data of poor users and non-poor users from the daily differential electricity consumption data by utilizing a statistical method. On the basis, the test sample group is verified, and a poor user identification method is perfected. According to the technical scheme, the influence of subjective factors is reduced, and the user group classification accuracy is effectively improved; the recognition efficiency is high, the coverage range is wide, and a large amount of manpower and material resources are saved.

Description

technical field [0001] The invention relates to a poor user identification method, in particular to a poor user identification method based on daily differential power consumption. Background technique [0002] At this stage, the identification method for poor users is usually issued step by step from the city to the county to the village, and then the village government conducts on-site investigations to confirm the type of each household and reports the summary. Low, wasting a lot of manpower and material resources. With the rapid development of smart grids, a large amount of electricity consumption data has been accumulated. Due to the huge differences in various factors such as economic level, living habits, and living regions of different resident groups, their power consumption levels are often very different. [0003] The State Grid Power Consumption Information Collection System is a system that collects, processes and monitors power consumption information of power...

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): G06K9/62G06Q50/06
CPCG06Q50/06G06F18/24323G06F18/214
Inventor 汪志奕戴向文谢岳应张驰陈佳怡江硕潘一洲卢旭航
Owner STATE GRID ZHEJIANG ELECTRIC POWER CO LTD JINHUA POWER SUPPLY CO
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