Electricity Theft Detection in Incremental Scenario: A Novel Semi-supervised Approach based on Hybrid Replay Strategy

Deep learning (DL) has achieved great success in the field of electricity theft detection (ETD). Most existing studies have used supervised mode to complete the DL-based ETD, but they do not have the capability of incremental detection, especially in small sample size scenarios. To address this prob...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on instrumentation and measurement Vol. 72; p. 1
Main Authors:	Yao, Ruizhe, Wang, Ning, Ke, Weipeng, Liu, Zhili, Yan, Zhenhong, Sheng, Xianjun
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.01.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Behavioral sciences Biological system modeling Boosting Convolutional neural networks Data models Deep learning Electricity Electricity theft detection Feature extraction Irish smart energy trial Support vector machines Temporal convolutional attention networks Theft Variational autoencoder
ISSN:	0018-9456, 1557-9662
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Deep learning (DL) has achieved great success in the field of electricity theft detection (ETD). Most existing studies have used supervised mode to complete the DL-based ETD, but they do not have the capability of incremental detection, especially in small sample size scenarios. To address this problem, this paper proposes a semi-supervised ETD approach based on hybrid replay strategy. From the data perspective, this paper designs a hybrid replay strategy that includes a variational autoencoder (VAE) and sample scrambling ranking (SSR) methods, and uses a "rehearsal" method to obtain incremental ETD capability. From the detection method perspective, this paper designs a semi-supervised ETD architecture that uses a temporal convolutional attention network (TCAN) as a feature extractor and uses contrastive learning to improve the utilization of unlabeled sensing samples, thus reducing the labeled sample size required for the fine-tuning process. Experimental results on the Irish smart energy trial (ISET) dataset show that the proposed scheme effectively solves the problem of incremental ETD in small sample size, and achieves 92.72%, 92.70%, 92.57% on accuracy, precision, and f1-score, respectively.
AbstractList	Deep learning (DL) has achieved great success in the field of electricity theft detection (ETD). Most existing studies have used supervised mode to complete the DL-based ETD, but they do not have the capability of incremental detection, especially in small sample size scenarios. To address this problem, this paper proposes a semi-supervised ETD approach based on hybrid replay strategy. From the data perspective, this paper designs a hybrid replay strategy that includes a variational autoencoder (VAE) and sample scrambling ranking (SSR) methods, and uses a "rehearsal" method to obtain incremental ETD capability. From the detection method perspective, this paper designs a semi-supervised ETD architecture that uses a temporal convolutional attention network (TCAN) as a feature extractor and uses contrastive learning to improve the utilization of unlabeled sensing samples, thus reducing the labeled sample size required for the fine-tuning process. Experimental results on the Irish smart energy trial (ISET) dataset show that the proposed scheme effectively solves the problem of incremental ETD in small sample size, and achieves 92.72%, 92.70%, 92.57% on accuracy, precision, and f1-score, respectively. Deep learning (DL) has achieved great success in the field of electricity theft detection (ETD). Most existing studies have used supervised mode to complete the DL-based ETD, but they do not have the capability of incremental detection, especially in small-sample size scenarios. To address this problem, this article proposes a semi-supervised ETD approach based on a hybrid replay strategy. From the data perspective, this article designs a hybrid replay strategy that includes a variational autoencoder (VAE) and sample scrambling ranking (SSR) methods, and uses a “rehearsal” method to obtain incremental ETD capability. From the detection method perspective, this article designs a semi-supervised ETD architecture that uses a temporal convolutional attention network (TCAN) as a feature extractor and uses contrastive learning to improve the utilization of unlabeled sensing samples, thus reducing the labeled sample size required for the fine-tuning process. Experimental results on the Irish smart energy trial (ISET) dataset show that the proposed scheme effectively solves the problem of incremental ETD in small sample size, and achieves 92.72%, 92.70%, and 92.57% on accuracy, precision, and f1-score, respectively.
Author	Yao, Ruizhe Wang, Ning Yan, Zhenhong Ke, Weipeng Liu, Zhili Sheng, Xianjun
Author_xml	– sequence: 1 givenname: Ruizhe orcidid: 0000-0002-0379-4948 surname: Yao fullname: Yao, Ruizhe organization: Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China – sequence: 2 givenname: Ning orcidid: 0000-0002-8476-0570 surname: Wang fullname: Wang, Ning organization: Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China – sequence: 3 givenname: Weipeng orcidid: 0000-0003-4986-0792 surname: Ke fullname: Ke, Weipeng organization: Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China – sequence: 4 givenname: Zhili orcidid: 0000-0003-1100-4261 surname: Liu fullname: Liu, Zhili organization: Electric Power Research Institute, State Grid Liaoning Electric Power Supply Co.Ltd, Shenyang, China – sequence: 5 givenname: Zhenhong orcidid: 0000-0002-3443-6916 surname: Yan fullname: Yan, Zhenhong organization: Electric Power Research Institute, State Grid Liaoning Electric Power Supply Co.Ltd, Shenyang, China – sequence: 6 givenname: Xianjun orcidid: 0000-0003-1694-4463 surname: Sheng fullname: Sheng, Xianjun organization: Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China
BookMark	eNp9kDFPwzAQhS1UJNrCzsBgiTnFdhLbYatKoZUKSLTMkeNeqKs0CY5TKf8eR-2AGJhO93Tv3t03QoOyKgGhW0omlJLkYbN8nTDCwkkYsoiL6AINaRyLIOGcDdCQECqDJIr5FRo1zZ4QIngkhqidF6CdNdq4Dm92kDv8BM5LpiqxKfGy1BYOUDpV4LWGUllTPeIpfquO4BU4mKBpa7BH08AWT-vaVkrvcKb61q9YdJk1W_wBdaE6vHZWOfjqrtFlrooGbs51jD6f55vZIli9vyxn01WgWcJcACBAqS3LNNNSi0gQHcWUM00oFUCVzmLgIqMcZCRiSCQkWoW5VoqKXLIwHKP7015_1ncLjUv3VWtLH5kyKWlMhJSJnyKnKW2rprGQp7U1B2W7lJK0h5t6uGkPNz3D9Rb-x-IBqh6a_9AU_xnvTkYDAL9ymORMyPAH4GiKXw
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_1109_TII_2024_3371991 crossref_primary_10_1016_j_ijepes_2025_110461 crossref_primary_10_1016_j_measurement_2025_117768 crossref_primary_10_1109_TIM_2024_3370803 crossref_primary_10_1109_TIM_2025_3602529 crossref_primary_10_1016_j_aej_2025_07_040 crossref_primary_10_1109_TIM_2024_3470061 crossref_primary_10_1109_TIM_2025_3595249 crossref_primary_10_1016_j_ijepes_2024_110309 crossref_primary_10_1109_TII_2024_3485813
Cites_doi	10.1007/s10489-022-04069-z 10.1016/j.neucom.2020.03.085 10.1016/j.epsr.2020.106904 10.1109/TIM.2023.3265739 10.1109/TIM.2022.3189748 10.1007/s10489-020-02049-9 10.1109/JSEN.2022.3147016 10.1109/TSG.2021.3088879 10.1109/JSYST.2020.3030238 10.1016/j.jpdc.2021.03.002 10.1109/TIM.2022.3201569 10.1109/TIM.2020.3048784 10.1109/JSEN.2020.3041322 10.1109/TIM.2021.3067216 10.1109/JSEN.2019.2902357 10.1016/j.apenergy.2019.01.076 10.1016/j.bdr.2021.100285 10.1016/j.ijepes.2020.106448 10.1109/TPWRS.2019.2943115 10.1109/TSG.2019.2892595 10.1155/2019/4136874 10.1109/TSG.2015.2425222 10.1109/TSG.2020.3047864 10.1016/j.ijepes.2020.106162 10.1109/TII.2019.2944880 10.3390/s21020626 10.1109/TIM.2021.3080390 10.3390/en13215758 10.1109/TIM.2019.2954722 10.4236/jpee.2016.49001 10.1109/TSG.2016.2574714 10.1109/TIM.2022.3162265 10.1016/j.ijepes.2020.106544 10.1109/TII.2016.2543145 10.1109/JSAC.2013.130714 10.1109/TSG.2021.3134018 10.1109/CVPR46437.2021.00812
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TIM.2023.3324674
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	1
ExternalDocumentID	10_1109_TIM_2023_3324674 10286278
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 5207052294 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ 5VS 8WZ A6W AAYXX AETIX AGSQL AI. AIBXA ALLEH CITATION EJD H~9 IAAWW IBMZZ ICLAB IDIHD IFJZH VH1 VJK 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c292t-ee7eaad2bc2c8c7470c45162c0117e1acb5e67b16e8475e98e9ca3fcaa17f8233
IEDL.DBID	RIE
ISICitedReferencesCount	14
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001090941700022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9456
IngestDate	Mon Jun 30 08:27:35 EDT 2025 Tue Nov 18 22:25:23 EST 2025 Sat Nov 29 04:38:40 EST 2025 Wed Aug 27 02:24:51 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c292t-ee7eaad2bc2c8c7470c45162c0117e1acb5e67b16e8475e98e9ca3fcaa17f8233
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-1100-4261 0000-0003-1694-4463 0000-0002-8476-0570 0000-0002-0379-4948 0000-0003-4986-0792 0000-0002-3443-6916
PQID	2881507889
PQPubID	85462
PageCount	1
ParticipantIDs	ieee_primary_10286278 crossref_primary_10_1109_TIM_2023_3324674 proquest_journals_2881507889 crossref_citationtrail_10_1109_TIM_2023_3324674
PublicationCentury	2000
PublicationDate	2023-01-01
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– month: 01 year: 2023 text: 2023-01-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 (ref37) 2023 ref24 ref23 ref26 ref25 ref20 ref21 ref28 ref27 ref29 tehrani (ref22) 2022; 208 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref31 doi: 10.1007/s10489-022-04069-z – ident: ref20 doi: 10.1016/j.neucom.2020.03.085 – ident: ref19 doi: 10.1016/j.epsr.2020.106904 – ident: ref33 doi: 10.1109/TIM.2023.3265739 – ident: ref28 doi: 10.1109/TIM.2022.3189748 – ident: ref34 doi: 10.1007/s10489-020-02049-9 – ident: ref2 doi: 10.1109/JSEN.2022.3147016 – ident: ref1 doi: 10.1109/TSG.2021.3088879 – ident: ref23 doi: 10.1109/JSYST.2020.3030238 – ident: ref27 doi: 10.1016/j.jpdc.2021.03.002 – ident: ref29 doi: 10.1109/TIM.2022.3201569 – ident: ref15 doi: 10.1109/TIM.2020.3048784 – ident: ref13 doi: 10.1109/JSEN.2020.3041322 – ident: ref14 doi: 10.1109/TIM.2021.3067216 – volume: 208 year: 2022 ident: ref22 article-title: Online electricity theft detection framework for large-scale smart grid data publication-title: Electr Power Syst Res – ident: ref4 doi: 10.1109/JSEN.2019.2902357 – year: 2023 ident: ref37 publication-title: Data from the Commission for Energy Regulation – ident: ref18 doi: 10.1016/j.apenergy.2019.01.076 – ident: ref21 doi: 10.1016/j.bdr.2021.100285 – ident: ref25 doi: 10.1016/j.ijepes.2020.106448 – ident: ref8 doi: 10.1109/TPWRS.2019.2943115 – ident: ref16 doi: 10.1109/TSG.2019.2892595 – ident: ref26 doi: 10.1155/2019/4136874 – ident: ref39 doi: 10.1109/TSG.2015.2425222 – ident: ref24 doi: 10.1109/TSG.2020.3047864 – ident: ref30 doi: 10.1016/j.ijepes.2020.106162 – ident: ref3 doi: 10.1109/TII.2019.2944880 – ident: ref5 doi: 10.3390/s21020626 – ident: ref35 doi: 10.1109/TIM.2021.3080390 – ident: ref11 doi: 10.3390/en13215758 – ident: ref12 doi: 10.1109/TIM.2019.2954722 – ident: ref9 doi: 10.4236/jpee.2016.49001 – ident: ref10 doi: 10.1109/TSG.2016.2574714 – ident: ref36 doi: 10.1109/TIM.2022.3162265 – ident: ref17 doi: 10.1016/j.ijepes.2020.106544 – ident: ref6 doi: 10.1109/TII.2016.2543145 – ident: ref38 doi: 10.1109/JSAC.2013.130714 – ident: ref7 doi: 10.1109/TSG.2021.3134018 – ident: ref32 doi: 10.1109/CVPR46437.2021.00812
SSID	ssj0007647
Score	2.4394295
Snippet	Deep learning (DL) has achieved great success in the field of electricity theft detection (ETD). Most existing studies have used supervised mode to complete...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Behavioral sciences Biological system modeling Boosting Convolutional neural networks Data models Deep learning Electricity Electricity theft detection Feature extraction Irish smart energy trial Support vector machines Temporal convolutional attention networks Theft Variational autoencoder
Title	Electricity Theft Detection in Incremental Scenario: A Novel Semi-supervised Approach based on Hybrid Replay Strategy
URI	https://ieeexplore.ieee.org/document/10286278 https://www.proquest.com/docview/2881507889
Volume	72
WOSCitedRecordID	wos001090941700022&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: PRVIEE databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS-RAEC5UXFgP6rqK44s-7MVDZpJOph_eBh_owWFhXfAWOpUaGNCMmIww_97qTkaUxQVvIeluAl93fV91d1UB_EqTxCVISVSylo2YoSiyqSqj2ClLTClOmyIUm9Djsbm_t7-7YPUQC0NE4fIZ9f1jOMsvZzj3W2UDT4ZKarMKq1qrNljrzexqlbUJMhNewSwLlmeSsR3c3dz2fZnwfsryQensAweFoir_WOJAL1dbX_yxbdjsdKQYtcD_gBWqdmDjXXbBHfgWbndi_RPml6HYzRRZcgueGJNGXFATLmFVYloJNhLtNiGP-AepYv95diZGYjx7IX5Dj9Oonj95q1JTKUZdGnLhGbAUPMT1wsd9CRbzD24huoS3i134e3V5d34ddfUWIpRWNhGRJudKWaBEg-xnxOjL-Er0eeMocVgMSekiUcSUNiRryKJLJ-hcoidGpukerFWzivZBZM6kKXtL5JTLhgbNRLoha6WCPxiKsx4Mlgjk2CUj9zUxHvLglMQ2Z8xyj1neYdaD07ceT20ijv-03fUYvWvXwtODoyXKebdU61wa40WxMfbgk26H8N2P3m68HMFa8zynY1jHl2ZaP5-EWfgKk4rZ9w
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB7xWLTsgV0eK7oLiw9cOKRNnJfNrVpARUCFRJG4Rc5kKlWCFJEUqf-esZMi0AqkvUWJnUT67JlvbM98AIdhEJgAKfAK5rIeeyjydJgUnm8STexSTKpyJzaRDofq7k5ft8nqLheGiNzhM-raS7eXX0xxZpfKetYZJjJVy7AaR5H0m3StV8ObJlFTIjPgOczEYLEr6eve6Pyqa4XCuyETiCSN3nkhJ6vyjy12Dubs-3_-2g_YaJmk6DfQb8ISlVvw7U19wS1Yc-c7sdqG2amTu5kgk27BQ2NcixOq3TGsUkxKwWaiWSjkN94glRxBT49FXwynz8R36GHiVbNHa1cqKkS_LUQurA8sBL9iMLeZX4Lp_L2Zi7bk7XwHbs9OR38HXqu44KHUsvaIUjKmkDlKVMiRho9WyFeirRxHgcE8piTNg4TYqcWkFWk04RiNCdKxkmH4E1bKaUm7ICKjwpDjJTKJiWKFaixNzGwp5weK_KgDvQUCGbblyK0qxn3mwhJfZ4xZZjHLWsw6cPTa47EpxfFJ2x2L0Zt2DTwd2FugnLWTtcqkUpYWK6V_fdDtAL4ORleX2eX58OI3rNsvNcswe7BSP81oH77gcz2pnv64EfkCEJDdPg
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=Electricity+Theft+Detection+in+Incremental+Scenario%3A+A+Novel+Semi-Supervised+Approach+Based+on+Hybrid+Replay+Strategy&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Yao%2C+Ruizhe&rft.au=Wang%2C+Ning&rft.au=Ke%2C+Weipeng&rft.au=Liu%2C+Zhili&rft.date=2023-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=72&rft.spage=1&rft_id=info:doi/10.1109%2FTIM.2023.3324674&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon