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

Power distribution network heterogeneous data integration method and system

A heterogeneous data, distribution network technology, applied in data processing applications, instruments, character and pattern recognition, etc., can solve the problem that some samples and detection indicators are difficult to effectively use, waste of distribution network equipment detection resources, and complex and expensive detection equipment. and other problems, to achieve the effect of improving the asset management level, management level and effect improvement of the distribution network

Pending Publication Date: 2019-10-25
CHINA ELECTRIC POWER RES INST +1
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In actual production practice, due to the different detection conditions of distribution network equipment by local power companies, manufacturers and testing institutions, some detection equipment is more complicated and expensive, resulting in the detection indicators of most distribution network equipment samples are not exactly the same
Because the traditional distribution network data analysis technology requires the target samples to use the same detection indicators, it is difficult to effectively use some samples and detection indicators from different power companies, manufacturers and testing institutions, and the existing distribution network equipment Detection resources cause great waste
At the same time, this small sample situation also brings great challenges to distribution network data quality management, making traditional distribution network data analysis methods ineffective or even invalid

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
  • Power distribution network heterogeneous data integration method and system
  • Power distribution network heterogeneous data integration method and system
  • Power distribution network heterogeneous data integration method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] figure 1 It is a flow chart of a distribution network heterogeneous data integration method of the present invention, such as figure 1 As shown, a distribution network heterogeneous data integration method provided by the present invention includes:

[0065] Step S11, selecting a data sample set with complete measurement indicators from the heterogeneous database of the original distribution network;

[0066] Step S12, perform generative confrontation network training according to the data sample set, and generate a new database with an enlarged data sample size according to the new data samples obtained from the training and the original distribution network heterogeneous database;

[0067] Step S13, according to the new database, use the clustering algorithm to repair the data samples with missing measurement indicators in the original distribution network heterogeneous database, and output the distribution network heterogeneous data according to the repaired origina...

Embodiment 2

[0125] Based on the same inventive concept, the present invention also provides a distribution network heterogeneous data integration system, which may include:

[0126] The selection module is used to select a data sample set with complete measurement indicators from the heterogeneous database of the original distribution network;

[0127] The training module is used to train the data sample set through the generative confrontation network; generate a new database after expanding the data sample size according to the new data samples obtained from the training and the original distribution network heterogeneous database;

[0128] The repair module is used to repair the data samples with missing measurement indicators in the heterogeneous database of the original distribution network through a clustering algorithm;

[0129] The output module is used to output the heterogeneous data of the distribution network according to the repaired original distribution network heterogeneou...

Embodiment 3

[0143] Based on the research on the existing distribution network database integration technology, the present invention proposes a distribution network heterogeneous data integration method based on generative confrontation network, such as figure 2 shown. Specifically include the following steps:

[0144] Step 1. Read the heterogeneous data of the distribution network, establish a database, and initialize parameters, including:

[0145] established database

[0146] Initialize the discriminant rate threshold c=0.1, reduce the step size a=0.0025; set the neural network activation function g and f as the Sigmodal function; initialize the distance threshold R in the peak clustering algorithm 1 =0.15,R 2 =0.15 and clustering threshold k=3; initialize the center point set Centre=D; initialize the limited coverage peak point set Temp_Peaks={}.

[0147] Step 1 is an unnecessary step, and the parameters preset in step 1 can be called directly during the execution of steps 2-5...

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 power distribution network heterogeneous data integration method and system. The method comprises: selecting a data sample set with complete measurement indexes from an original power distribution network heterogeneous database; performing generative adversarial network training according to the data sample set, and generating a new database after data sample size expansion according to a new data sample obtained by training and an original power distribution network heterogeneous database; and according to the new database, repairing data samples with missing measurement indexes in the original power distribution network heterogeneous database through a clustering algorithm, and outputting power distribution network heterogeneous data according to the repaired original power distribution network heterogeneous database. The method can achieve the high-efficiency restoration of the missing data sample of the measurement index.

Description

technical field [0001] The invention belongs to the field of distribution network data quality management, and in particular relates to a distribution network heterogeneous data integration method and system. Background technique [0002] In actual production practice, due to the different detection conditions of distribution network equipment by local power companies, manufacturers and testing institutions, some testing equipment is more complicated and expensive, resulting in the detection indicators of most distribution network equipment samples are not exactly the same. Because the traditional distribution network data analysis technology requires the target samples to use the same detection indicators, it is difficult to effectively use some samples and detection indicators from different power companies, manufacturers and testing institutions, and the existing distribution network equipment Detection resources cause a great waste. At the same time, this small sample s...

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 Applications(China)
IPC IPC(8): G06K9/62G06Q10/06G06Q50/06
CPCG06Q10/0639G06Q50/06G06F18/241G06F18/214
Inventor 谈元鹏刘伟陈海赵明欣苏剑
Owner CHINA ELECTRIC POWER RES INST
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