Supercharge Your Innovation With Domain-Expert AI Agents!

Data filling method for intelligent electric meter based on variational auto-encoder

A smart meter and self-encoder technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., to achieve the effect of filling accurate data

Pending Publication Date: 2020-12-11
STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD HARBIN POWER SUPPLY CO +2
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are few studies on filling the missing data of smart meters. Therefore, it is necessary to provide one or more technical solutions that can at least solve the above technical problems

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 filling method for intelligent electric meter based on variational auto-encoder
  • Data filling method for intelligent electric meter based on variational auto-encoder
  • Data filling method for intelligent electric meter based on variational auto-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0116] Extract the load data of a power grid in Northeast China, and use the above method to cluster and generate scenarios. After clustering, the cluster centers of various internal loads are as follows: figure 2 As shown, four clusters are obtained. After clustering, various intraday load scenarios are as follows: image 3 As shown, seven original data curves were selected from each cluster, and different missing data time periods were set for them, that is, a total of 96 data points were obtained every day, one every 15 minutes, and the seven curves were respectively Set different missing time periods from 0:00 to 1:00, 3:00 to 4:00, 6:00 to 7:00, etc. Table 1 shows the filling effect of one of the two curves, and the missing time of curve one The segment is from 0:00 to 1:00, and the missing time segment of curve 2 is from 3:00 to 4:00;

[0117] Table 1

[0118]

[0119] The error in comparing the imputed data with the corresponding original data is measured as the m...

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 filling method for an intelligent electric meter based on a variation auto-encoder, and the method is specifically implemented according to the following steps: taking ahistorical daily load data set obtained in an intelligent electric meter as a clustering sample for clustering analysis, and obtaining type days with different power utilization characteristics, namely, clustering results; taking historical load data in dates contained in the clustering result as input, and generating a VAE-based massive daily load curve; establishing a mathematical model of discrete curve similarity, selecting a group with the highest daily similarity with the missing data by comparing with each clustering center, and finding out ten curves similar to the daily load curve ofthe missing data in shape from the group with the highest similarity to serve as historical daily load curves; and processing data corresponding to the similar historical daily load curve through animproved weighted average method to obtain a corresponding missing data prediction value, thereby realizing missing day intelligent electric meter load data filling. Missing data can be accurately filled through historical load data.

Description

technical field [0001] The invention belongs to the technical field of electrical data monitoring, and in particular relates to a method for filling data of an intelligent electric meter based on a variational autoencoder. Background technique [0002] The deployment and application of a large number of smart meters enables power companies to obtain measured data at the end of the distribution network with high frequency, wide coverage and consistent time scale. However, the observed value of the user's electricity load data is affected by various factors, and may be missing during collection and transmission. The lack of these data has a great negative impact on the correct establishment of load models, the mining of the intrinsic correlation and deep value of smart meter data, and the provision of decision support for power companies' commercial operations, grid planning, and operation and maintenance. Therefore, before analyzing the smart meter data, it is necessary to e...

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): G06K9/62
CPCG06F18/23G06F18/10
Inventor 唐晓博王东郭玉崔春徐新亮于喆张鑫鹏李字霞刘晶淳
Owner STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD HARBIN POWER SUPPLY CO
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com