Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things

In the construction of the ubiquitous power Internet of Things, it is indispensable to analyze customers′ electricity consumption behavior for power companies. In previous studies, the K-means clustering algorithm is one of the commonly used methods for analyzing customer electricity consumption beh...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Ying, XIANG Wen, ZHANG Qun, GAO Xiuyun
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2022-04-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413121103364096
author WANG Ying
XIANG Wen
ZHANG Qun
GAO Xiuyun
author_facet WANG Ying
XIANG Wen
ZHANG Qun
GAO Xiuyun
author_sort WANG Ying
collection DOAJ
description In the construction of the ubiquitous power Internet of Things, it is indispensable to analyze customers′ electricity consumption behavior for power companies. In previous studies, the K-means clustering algorithm is one of the commonly used methods for analyzing customer electricity consumption behavior. However, because the initial centroid is randomly selected, it is easy to fall into a local optimum and difficult to converge to a global minimum. To this problem, an improved K-means algorithm (DPSO-Kmeans) based on an improved dynamic particle swarm optimization algorithm is proposed and used in the analysis of customers′ electricity consumption behavior. In the experiment, the electricity consumption behavior records of 312 household users were used for cluster analysis. The results prove that DPSO-Kmeans has a better clustering effect than the traditional K-means algorithm, and can extract more typical customers′ electrical behavior pattern.
format Article
id doaj-art-2ae02ccf7d2a400bb8cbec0b8a0dabf8
institution Kabale University
issn 1007-2683
language zho
publishDate 2022-04-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-2ae02ccf7d2a400bb8cbec0b8a0dabf82025-08-20T03:34:13ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-04-01270210611310.15938/j.jhust.2022.02.014Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of ThingsWANG Ying0XIANG Wen1ZHANG Qun2GAO Xiuyun3College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China;Economic and Technological Research Institute of State Grid, Heilongjiang Electric Power Co., Ltd., Harbin 150036,ChinaCollege of Electrical and Information, Northeast Agriculture University, Harbin, 150038, China;Economic and Technological Research Institute of State Grid, Heilongjiang Electric Power Co., Ltd., Harbin 150036,ChinaEconomic and Technological Research Institute of State Grid, Heilongjiang Electric Power Co., Ltd., Harbin 150036,ChinaEconomic and Technological Research Institute of State Grid, Heilongjiang Electric Power Co., Ltd., Harbin 150036,ChinaIn the construction of the ubiquitous power Internet of Things, it is indispensable to analyze customers′ electricity consumption behavior for power companies. In previous studies, the K-means clustering algorithm is one of the commonly used methods for analyzing customer electricity consumption behavior. However, because the initial centroid is randomly selected, it is easy to fall into a local optimum and difficult to converge to a global minimum. To this problem, an improved K-means algorithm (DPSO-Kmeans) based on an improved dynamic particle swarm optimization algorithm is proposed and used in the analysis of customers′ electricity consumption behavior. In the experiment, the electricity consumption behavior records of 312 household users were used for cluster analysis. The results prove that DPSO-Kmeans has a better clustering effect than the traditional K-means algorithm, and can extract more typical customers′ electrical behavior pattern.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2082analysis of electricity consumptionk-means clustering algorithminitial centroiddynamic particle swarm algorithmelectricity usage behavior model
spellingShingle WANG Ying
XIANG Wen
ZHANG Qun
GAO Xiuyun
Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
Journal of Harbin University of Science and Technology
analysis of electricity consumption
k-means clustering algorithm
initial centroid
dynamic particle swarm algorithm
electricity usage behavior model
title Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
title_full Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
title_fullStr Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
title_full_unstemmed Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
title_short Analysis of Customer Power Consumption Behavior Based on DPSO-Kmeans under the Ubiquitous Power Internet of Things
title_sort analysis of customer power consumption behavior based on dpso kmeans under the ubiquitous power internet of things
topic analysis of electricity consumption
k-means clustering algorithm
initial centroid
dynamic particle swarm algorithm
electricity usage behavior model
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2082
work_keys_str_mv AT wangying analysisofcustomerpowerconsumptionbehaviorbasedondpsokmeansundertheubiquitouspowerinternetofthings
AT xiangwen analysisofcustomerpowerconsumptionbehaviorbasedondpsokmeansundertheubiquitouspowerinternetofthings
AT zhangqun analysisofcustomerpowerconsumptionbehaviorbasedondpsokmeansundertheubiquitouspowerinternetofthings
AT gaoxiuyun analysisofcustomerpowerconsumptionbehaviorbasedondpsokmeansundertheubiquitouspowerinternetofthings