Power failure sensitivity analysis method based on neural network and clustering

A technology of sensitivity analysis and neural network, applied in the application field of electric power big data, can solve the problems of no model and reference method, and achieve the effect of improving service level

Inactive Publication Date: 2020-07-14
STATE GRID HEBEI ENERGY TECH SERVICE CO LTD +2
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The research on sensitive customers is different from general qualitative classification problems. There are relatively few studies at present, and there are no clear models and methods that can be used for reference.

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 failure sensitivity analysis method based on neural network and clustering
  • Power failure sensitivity analysis method based on neural network and clustering
  • Power failure sensitivity analysis method based on neural network and clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059]In recent years, the number of work orders caused by frequent power outages has increased year by year, and the demands of sensitive users can largely reflect the improvement direction of the service quality of power supply units. In this example, based on the sample data of 95598 power outage work orders, firstly, the sensitive characteristics of power outage duration are studied through cluster analysis, and users in hundreds of counties are labeled. At the same time, combined with the user's sensitivity to power consumption, determine the factors that affect the power outage sensitivity, establish a line sensitivity neural network model that can reflect the characteristics of these factors, and predict the power outage work order for the power outage plan of the line, so as to realize whether the user is sensitive or not. Estimates, so as to formulate relevant outage plans according to local conditions, optimize outage process measures, and improve users' service perce...

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 power failure sensitivity analysis method based on a neural network and clustering. The power failure sensitivity analysis method comprises the steps of data preprocessing, clustering analysis, neural network model construction, power failure simulation prediction and power failure plan arrangement. According to the method, frequent power failure lines and corresponding sensitive users are comprehensively sorted through the power failure plan, the power failure sensitive characteristics of the users are extracted, the regional characteristics are researched, regionaltargeted and targeted designated feasible improvement and optimization measures are provided, and the service level of power supply is improved.

Description

technical field [0001] The invention relates to a power outage sensitivity analysis method, in particular to a power outage sensitivity analysis method based on a neural network and clustering, and belongs to the technical field of electric power big data application. Background technique [0002] In 2018, a power customer service center received a total of 560,000 work orders, of which complaints and repair work orders caused by power outages accounted for nearly 15%. Reducing complaints caused by power outages can greatly reduce the number of work orders accepted, which has a greater impact on improving the quality of power supply. Existing power outage sensitivity research basically selects impact indicators, builds test models through test data, determines index weights, and calculates whether it is a sensitive situation. Yang Hengcheng and Shuai Chunyan, in the article "Machine Learning-Based Analysis of Power Customers and Outage Sensitivity", analyzed users through d...

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): G06Q10/04G06Q50/06G06K9/62G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/08G06N3/045G06F18/231G06F18/23G06F18/23213
Inventor 武光华张世科刘二刚李倩柳长发
Owner STATE GRID HEBEI ENERGY TECH SERVICE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap