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

User power consumption behavior analysis method based on feature optimization and auxiliary clustering

A feature optimization and behavior analysis technology, applied in data processing applications, instruments, calculations, etc., can solve problems that are not suitable for user power consumption data analysis, falling into local optimum, etc., to improve classification efficiency, optimize clustering centers, and improve clustering The effect of class performance

Pending Publication Date: 2022-07-29
GUANGXI POWER GRID CO LTD NANNING POWER SUPPLY BUREAU
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a user electricity consumption behavior analysis method based on feature optimization and auxiliary clustering, which can solve the problem that most of the clustering methods in the prior art are easily affected by the position of the initial cluster center and fall into local optimum, which is not suitable for The problem of user electricity consumption data analysis under

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
  • User power consumption behavior analysis method based on feature optimization and auxiliary clustering
  • User power consumption behavior analysis method based on feature optimization and auxiliary clustering
  • User power consumption behavior analysis method based on feature optimization and auxiliary clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0124] According to the proposed method, the daily load curve of 500 users in a certain area in a week is used to simulate. The data set takes 30 minutes as a cycle, and 336 measurement points are selected. In order to fully verify the feasibility of the proposed scheme, the following comparison schemes are set up:

[0125] M1: k-means clustering using raw data;

[0126] M2: Perform k-means cluster analysis on the original data to construct load characteristic indicators;

[0127] M3: Use UMAP to perform cluster analysis on raw data dimensionality reduction combined with k-means;

[0128] M4: Use the original data to use SSA to optimize k-means for cluster analysis;

[0129] M5: K-means clustering analysis using UMAP combined with constructing weights to optimize load characteristic indicators for dimensionality reduction;

[0130] M6: Use UMAP combined with weight optimization indicators to construct dimensionality reduction, and use SSA to optimize k-meams for cluster an...

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 user power consumption behavior analysis method based on feature optimization and auxiliary clustering, and the method comprises the following steps: carrying out the conversion from high-dimensional data to low-dimensional data based on UMAP data dimension reduction, and generating a data set containing dimension reduction features; inputting user power consumption data as a feature vector, constructing a feature index, endowing a weight by using a CRITIC weight method, and combining with the data set to obtain an optimized feature set; and based on the optimized feature set, user behavior analysis is carried out through a k-means clustering method optimized by a sparrow algorithm. According to the method, k-means clustering is improved based on the sparrow search algorithm, the clustering center is optimized, the clustering performance is improved, the reasonability of user classification is further improved, the user classification efficiency is improved, and different types of power consumption behaviors are accurately obtained.

Description

technical field [0001] The invention relates to the technical field of user electricity consumption behavior analysis, in particular to a user electricity consumption behavior analysis method based on feature optimization and auxiliary clustering. Background technique [0002] Electric energy is an important energy source for national operation, and it is moving from the traditional power system to a new direction, namely the smart grid. The essence of smart grid is the application of big data in the power industry. It generates real-time grid panoramic real-time data during operation, data generated by equipment monitoring, power consumption data collected by smart terminals, and external energy, weather, etc. collected during the application process. Multiple types of data are growing exponentially, accumulating massive multi-source data. With the transformation of the traditional power system to the smart grid, the widespread use of smart terminals, the interaction betwe...

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
CPCG06Q10/06393G06Q50/06G06F18/23213G06F18/241
Inventor 鲍海波黄晓胜郭小璇李江伟李绍坚陈子民莫江婷陈广生
Owner GUANGXI POWER GRID CO LTD NANNING POWER SUPPLY BUREAU
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