Anomaly electricity detection method based on entropy weight method and isolated forest algorithm

This study aims at investigating the applicability of abnormal electricity consumption data detection method, which is based on the entropy weight method and the isolated forest tree algorithm. The inaccessibility and imbalance of abnormal electricity consumption samples in actual data sets are cons...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in energy research Jg. 10
Hauptverfasser: Jianyuan, Wang, Chengcheng, Gu, Kechen, Liu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Frontiers Media S.A 31.08.2022
Schlagworte:
ISSN:2296-598X, 2296-598X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This study aims at investigating the applicability of abnormal electricity consumption data detection method, which is based on the entropy weight method and the isolated forest tree algorithm. The inaccessibility and imbalance of abnormal electricity consumption samples in actual data sets are considered by analyzing smart distribution network power consumption big data. Firstly, the users are classified by the k-means clustering algorithm, and then the characteristics of each type of user are extracted and the feature set is processed by the principal component analysis method to reduce the dimensions, followed by the entropy weight method adaptive configuration of the weight coefficients of each feature index, and finally the abnormal power consumption users are calculated based on the feature-weighted isolated forest algorithm. The algorithm verifies the real electricity consumption data of 6,445 users, and the results show that the method has a high detection accuracy, recall rate and F1 score, which is more suitable for the detection of abnormal electricity consumption in scenarios when there are complex and diverse user power consumption behaviors.
AbstractList This study aims at investigating the applicability of abnormal electricity consumption data detection method, which is based on the entropy weight method and the isolated forest tree algorithm. The inaccessibility and imbalance of abnormal electricity consumption samples in actual data sets are considered by analyzing smart distribution network power consumption big data. Firstly, the users are classified by the k-means clustering algorithm, and then the characteristics of each type of user are extracted and the feature set is processed by the principal component analysis method to reduce the dimensions, followed by the entropy weight method adaptive configuration of the weight coefficients of each feature index, and finally the abnormal power consumption users are calculated based on the feature-weighted isolated forest algorithm. The algorithm verifies the real electricity consumption data of 6,445 users, and the results show that the method has a high detection accuracy, recall rate and F1 score, which is more suitable for the detection of abnormal electricity consumption in scenarios when there are complex and diverse user power consumption behaviors.
Author Jianyuan, Wang
Kechen, Liu
Chengcheng, Gu
Author_xml – sequence: 1
  givenname: Wang
  surname: Jianyuan
  fullname: Jianyuan, Wang
– sequence: 2
  givenname: Gu
  surname: Chengcheng
  fullname: Chengcheng, Gu
– sequence: 3
  givenname: Liu
  surname: Kechen
  fullname: Kechen, Liu
BookMark eNp1kNtKAzEQhoNUUGsfwLt9gdZJstlNLot4KAjeKHgXZrOTNmW7KdmA9O3dWgURvBjm-P8M3xWb9LEnxm44LKTU5tZTn9YLAUIsjC7LWp6xSyFMNVdGv09-1RdsNgxbAOBSqJLDJcNlH3fYHQrqyOUUXMiHoqU8NiH2xY7yJrZFgwO1xdhTn1PcH4oPCutN_llj3xZhiB3m8crHREMusFvHFPJmd83OPXYDzb7zlL093L_ePc2fXx5Xd8vnuZOqzHPlZOmhJqXByAq4caLSzlTYIPoaQLWi8sYASJLcU6PQewXka9X6qjFGTtnq5NtG3Np9CjtMBxsx2K9BTGuLKQfXkdWmEpWo_Riq1A3XtSgJBNfoWqNqGL3qk5dLcRgSeTtywSORnDB0loM9grdf4O0RvD2BH5X8j_Lnk_81n5MdiqY
CitedBy_id crossref_primary_10_1007_s10489_025_06663_3
crossref_primary_10_1016_j_energy_2025_138053
crossref_primary_10_1088_1361_6579_acff35
crossref_primary_10_1049_tje2_12380
crossref_primary_10_3390_en17122988
crossref_primary_10_3390_en18143722
crossref_primary_10_1038_s41598_025_96612_4
crossref_primary_10_1109_JSEN_2024_3426090
crossref_primary_10_3390_s25175265
Cites_doi 10.1109/tii.2017.2785963
10.13335/j.1000-3673.pst.2018.0765
10.1016/j.ijepes.2011.09.009
10.1016/j.knosys.2020.106490
10.1109/TCCN.2019.2911524
10.7500/AEPS20200505018
10.1109/access.2020.2980079
10.1016/j.ijepes.2020.106448
10.1016/s0893-6080(00)00026-5
10.3969/j.issn.1000-7229.2016.07.001
10.1016/0169-7439(87)80084-9
10.1109/tpwrd.2015.2479941
10.13334/j.0258-8013.pcsee.2016.02.008
10.7500/AEPS20200511001
10.1109/tpwrs.2008.926431
10.7500/AEPS20181115008
10.3745/kipstb.2007.14-b.4.287
10.19783/j.cnki.pspc.201267
10.19783/j.cnki.pspc.200573
10.1109/tii.2018.2873814
10.1109/tpwrd.2011.2161621
10.3969/j.issn.2095-0020.2014.03.002
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.3389/fenrg.2022.984473
DatabaseName CrossRef
DOAJ Open Access Full Text
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2296-598X
ExternalDocumentID oai_doaj_org_article_8962627f627548b18724e0218acd9570
10_3389_fenrg_2022_984473
GroupedDBID 5VS
9T4
AAFWJ
AAYXX
ACGFS
ADBBV
AFPKN
ALMA_UNASSIGNED_HOLDINGS
BCNDV
CITATION
GROUPED_DOAJ
KQ8
M~E
OK1
ID FETCH-LOGICAL-c354t-5c34f07e580936019c268c96abaaf7005d26f99003e31feb5aff50ef75df6b993
IEDL.DBID DOA
ISICitedReferencesCount 12
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000863171900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2296-598X
IngestDate Fri Oct 03 12:51:30 EDT 2025
Sat Nov 29 04:19:21 EST 2025
Tue Nov 18 21:18:28 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c354t-5c34f07e580936019c268c96abaaf7005d26f99003e31feb5aff50ef75df6b993
OpenAccessLink https://doaj.org/article/8962627f627548b18724e0218acd9570
ParticipantIDs doaj_primary_oai_doaj_org_article_8962627f627548b18724e0218acd9570
crossref_citationtrail_10_3389_fenrg_2022_984473
crossref_primary_10_3389_fenrg_2022_984473
PublicationCentury 2000
PublicationDate 2022-08-31
PublicationDateYYYYMMDD 2022-08-31
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-08-31
  day: 31
PublicationDecade 2020
PublicationTitle Frontiers in energy research
PublicationYear 2022
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Xu (B16) 2021; 49
Song (B13) 2019; 43
Huang (B4) 2021; 125
Angelos (B1) 2011; 26
Hu (B3) 2019; 43
Mortaz (B10) 2020; 210
Xu (B17) 2015; 32
(B2) 2011
Zhang (B20) 2020; 8
Yu (B18) 2021; 45
Kim (B6) 2007; 14
Song (B14) 2016; 37
Zhuang (B24) 2016; 36
Rajendran (B12) 2019; 5
Nizar (B11) 2008; 23
Hyvärinen (B5) 2000; 13
Wold (B15) 1987; 2
Monedero (B9) 2012; 34
Zheng (B23) 2018; 14
Zheng (B22) 2019; 15
Liu (B8) 2020; 44
Zhang (B21) 2021; 49
Li (B7) 2019; 43
Zhang (B19) 2014; 17
References_xml – volume: 14
  start-page: 1606
  year: 2018
  ident: B23
  article-title: Wide and deep convolutional neural networks for electricity-theft detection to secure smart grids
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/tii.2017.2785963
– volume: 43
  start-page: 1447
  year: 2019
  ident: B7
  article-title: Anomaly detection method of power dispatch flow data based on isolated forest algorithm
  publication-title: Power Grid Technol.
  doi: 10.13335/j.1000-3673.pst.2018.0765
– volume: 34
  start-page: 90
  year: 2012
  ident: B9
  article-title: Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees
  publication-title: Int. J. Electr. Power & Energy Syst.
  doi: 10.1016/j.ijepes.2011.09.009
– volume: 210
  start-page: 106490
  year: 2020
  ident: B10
  article-title: Imbalance accuracy metric for model selection in multi-class imbalance classification problems
  publication-title: Knowledge-Based Syst.
  doi: 10.1016/j.knosys.2020.106490
– volume: 5
  start-page: 637
  year: 2019
  ident: B12
  article-title: Unsupervised wireless spectrum anomaly detection with interpretable features
  publication-title: IEEE Trans. Cogn. Commun. Netw.
  doi: 10.1109/TCCN.2019.2911524
– volume: 44
  start-page: 28
  year: 2020
  ident: B8
  article-title: A deep end-to-end super-resolution perception method for power distribution side load data
  publication-title: Automation Electr. Power Syst.
  doi: 10.7500/AEPS20200505018
– volume: 8
  start-page: 55483
  year: 2020
  ident: B20
  article-title: Unsupervised detection of abnormal electricity consumption behavior based on feature engineering
  publication-title: IEEE Access
  doi: 10.1109/access.2020.2980079
– volume: 43
  start-page: 119
  year: 2019
  ident: B3
  article-title: Nontechnical loss detection based on stacked uncorrelating autoencoder and support vector machine
  publication-title: Automation Electr. Power Syst.
– volume: 125
  start-page: 106448
  year: 2021
  ident: B4
  article-title: Electricity theft detection based on stacked sparse denoising autoencoder
  publication-title: Int. J. Electr. Power & Energy Syst.
  doi: 10.1016/j.ijepes.2020.106448
– volume: 13
  start-page: 411
  year: 2000
  ident: B5
  article-title: Independent component analysis:algorithms and applications
  publication-title: Neural Netw.
  doi: 10.1016/s0893-6080(00)00026-5
– volume: 37
  start-page: 1
  year: 2016
  ident: B14
  article-title: Review of China's smart grid technology development practice
  publication-title: Electr. Power Constr.
  doi: 10.3969/j.issn.1000-7229.2016.07.001
– volume: 2
  start-page: 37
  year: 1987
  ident: B15
  article-title: Principal component analysis
  publication-title: Chemom. Intell. Lab. Syst.
  doi: 10.1016/0169-7439(87)80084-9
– volume: 32
  start-page: 609
  year: 2015
  ident: B17
  article-title: Hierarchical K-means method for clustering large-scale advanced metering infrastructure data
  publication-title: IEEE Trans. Power Deliv.
  doi: 10.1109/tpwrd.2015.2479941
– volume: 36
  start-page: 379
  year: 2016
  ident: B24
  article-title: Anomaly detection for power consumption patterns based on unsupervised learning
  publication-title: Proc. CSEE
  doi: 10.13334/j.0258-8013.pcsee.2016.02.008
– volume: 45
  start-page: 144
  year: 2021
  ident: B18
  article-title: Multi-label text classification for power ICT custom service system based on binary relevance and gradient boosting decision tree
  publication-title: Automation Electr. Power Syst.
  doi: 10.7500/AEPS20200511001
– volume: 23
  start-page: 946
  year: 2008
  ident: B11
  article-title: Power utility nontechnical loss analysis with extreme learning machine method
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/tpwrs.2008.926431
– volume: 43
  start-page: 65
  year: 2019
  ident: B13
  article-title: Daily load curve clustering method based on feature index dimension reduction and entropy weight method
  publication-title: Automation Electr. Power Syst.
  doi: 10.7500/AEPS20181115008
– year: 2011
  ident: B2
  article-title: The commission for Energy regulation(CER)-smart-metering project[EB/OL].[2011-05-16]
– volume: 14
  start-page: 287
  year: 2007
  ident: B6
  article-title: Improved focused sampling for class imbalance problem
  publication-title: KIPS Transactions:PartB
  doi: 10.3745/kipstb.2007.14-b.4.287
– volume: 49
  start-page: 12
  year: 2021
  ident: B16
  article-title: Identification of abnormal line loss for a distribution power network based on an isolation forest algorithm
  publication-title: Power Syst. Prot. Control
  doi: 10.19783/j.cnki.pspc.201267
– volume: 49
  start-page: 180
  year: 2021
  ident: B21
  article-title: A review of smart grid development in China
  publication-title: Power Syst. Prot. Control
  doi: 10.19783/j.cnki.pspc.200573
– volume: 15
  start-page: 1809
  year: 2019
  ident: B22
  article-title: A novel combined data-driven approach for electricity theft detection
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/tii.2018.2873814
– volume: 26
  start-page: 2436
  year: 2011
  ident: B1
  article-title: Detection and identification of abnormalities in customer consumptions in power distribution systems
  publication-title: IEEE Trans. Power Deliv.
  doi: 10.1109/tpwrd.2011.2161621
– volume: 17
  start-page: 132
  year: 2014
  ident: B19
  article-title: Outlier mining based on kernel local outlier factor
  publication-title: J. Shanghai Dianji Univ.
  doi: 10.3969/j.issn.2095-0020.2014.03.002
SSID ssj0001325410
Score 2.3135805
Snippet This study aims at investigating the applicability of abnormal electricity consumption data detection method, which is based on the entropy weight method and...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
SubjectTerms abnormal power consumption detection
entropy weight method
isolation forest algorithm
kmeans clustering algorithm
principal component dimension 11
Title Anomaly electricity detection method based on entropy weight method and isolated forest algorithm
URI https://doaj.org/article/8962627f627548b18724e0218acd9570
Volume 10
WOSCitedRecordID wos000863171900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ
  customDbUrl:
  eissn: 2296-598X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001325410
  issn: 2296-598X
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2296-598X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001325410
  issn: 2296-598X
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELVQxQAD4lN8ywMTUmhiO7E9AmrFQsUAUrfI8Uep1KZVCaAu_HbOTlqFBRaWSEmcyHo56967WO8QuqKw_oE5mEhYIiNG_JorhIskpDKjnVMg4EKzCT4YiOFQPrVaffk9YbU9cA1cV0ig3IQ776bLRJEITpj1iUlpI1Me1DqwnpaYCtUVCsInaX5jggqTXQefYwR6kJAbKRjj9Eciavn1h8TS30U7DSPEt_VM9tCGLffRdssn8AApEOlTNVniumnNWAN1xsZWYRtViesu0NgnJIPh3BdsZ_Ml_gxlz9VtVRo8hkgDcmkwUFVIB1hNRrPFuHqdHqKXfu_5_iFqeiNEmqasilJNmYu5TUUsKYgqqUkmtMxUoZTjsLQMyZz0ZUpLE2eLVDmXxtbx1LisAFJyhDrlrLTHCFPPA3gRU2c4M1IXxpvgG1kkTisTuxMUr4DKdWMc7vtXTHIQEB7bPGCbe2zzGtsTdL1-ZF67Zvw2-M6jvx7oDa_DBQiDvAmD_K8wOP2Pl5yhLT-vumR8jjrV4t1eoE39UY3fFpchwuD4-NX7BkCG1hI
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Anomaly+electricity+detection+method+based+on+entropy+weight+method+and+isolated+forest+algorithm&rft.jtitle=Frontiers+in+energy+research&rft.au=Wang+Jianyuan&rft.au=Gu+Chengcheng&rft.au=Liu+Kechen&rft.date=2022-08-31&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-598X&rft.volume=10&rft_id=info:doi/10.3389%2Ffenrg.2022.984473&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_8962627f627548b18724e0218acd9570
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-598X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-598X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-598X&client=summon