Anomaly Detection, Localization and Classification Using Drifting Synchrophasor Data Streams

With ongoing automation and digitization of the electric power system, several Phasor Measurement Units (PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms o...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on smart grid Ročník 12; číslo 4; s. 3570 - 3580
Hlavní autori:	Ahmed, A., Sajan, K. S., Srivastava, A., Wu, Y.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 01.07.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Algorithms Anomalies anomaly and event classification Anomaly detection Classification Data transmission Deep learning Distance learning Distributed generation Electric power grids Electric power systems Electrical loads Electricity distribution Energy sources Fault detection Heuristic algorithms Localization Machine learning Measuring instruments Multivariate analysis Online instruction Phasor measurement units Phasors Power system dynamics Real time Real-time systems Stress concentration Switching Training
ISSN:	1949-3053, 1949-3061
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	With ongoing automation and digitization of the electric power system, several Phasor Measurement Units (PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real-time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This article proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm. Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% - 10% in terms of accuracy, false-positive rate, and false-negative rate.
AbstractList	With ongoing automation and digitization of the electric power system, several Phasor Measurement Units (PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real-time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This article proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm. Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% – 10% in terms of accuracy, false-positive rate, and false-negative rate.
Author	Srivastava, A. Wu, Y. Ahmed, A. Sajan, K. S.
Author_xml	– sequence: 1 givenname: A. surname: Ahmed fullname: Ahmed, A. email: anurag.k.srivastava@wsu.edu organization: School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA – sequence: 2 givenname: K. S. surname: Sajan fullname: Sajan, K. S. organization: School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA – sequence: 3 givenname: A. orcidid: 0000-0003-3518-8018 surname: Srivastava fullname: Srivastava, A. organization: School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA – sequence: 4 givenname: Y. surname: Wu fullname: Wu, Y. organization: Computer and Data Science Department, Case Western Reserve University, Cleveland, OH, USA
BookMark	eNp9kM9PwjAUxxuDiYjcTbws8erwtV03eiSgaELiAbiZNLVrpWSs2JYD_vVujnDw4Lu8n9_3TT7XqFe7WiN0i2GEMfDH1XI-IkDwiALLaMEuUB_zjKcUctw714xeoWEIW2iCUpoT3kfvk9rtZHVMZjpqFa2rH5KFU7Ky37LtElmXybSSIVhjVTdaB1t_JjNvTWyL5bFWG-_2GxmcT2YyymQZvZa7cIMujayCHp7yAK2fn1bTl3TxNn-dThapIhzHFKuCjpXK9AehpASuCs0NhbIEKE1pOIVsLIEVRpIyLwjWusjHmhdjljFGuKQDdN_93Xv3ddAhiq07-LqxFIRlhAGQjDdX0F0p70Lw2oi9tzvpjwKDaDGKBqNoMYoTxkaS_5EoG38hRC9t9Z_wrhNarfXZh1PKeLP9AR-bgTw
CODEN	ITSGBQ
CitedBy_id	crossref_primary_10_1016_j_apenergy_2022_119608 crossref_primary_10_1145_3746635 crossref_primary_10_1109_ACCESS_2023_3330056 crossref_primary_10_1109_JIOT_2022_3183180 crossref_primary_10_3390_app14031194 crossref_primary_10_1109_JIOT_2023_3286185 crossref_primary_10_1186_s13677_024_00682_0 crossref_primary_10_3390_ijgi11030205 crossref_primary_10_1007_s12065_025_01079_x crossref_primary_10_1109_TSG_2023_3270421 crossref_primary_10_1016_j_apenergy_2023_121573 crossref_primary_10_1109_TSG_2023_3325276 crossref_primary_10_1109_ACCESS_2022_3205321 crossref_primary_10_1098_rsta_2022_0253 crossref_primary_10_1109_JPROC_2022_3175070 crossref_primary_10_1016_j_energy_2023_130184 crossref_primary_10_1016_j_ijepes_2023_108988 crossref_primary_10_1109_TIA_2025_3529800 crossref_primary_10_1109_TIA_2024_3471997 crossref_primary_10_1016_j_epsr_2024_110538 crossref_primary_10_1109_TSMC_2024_3407061 crossref_primary_10_3390_math10213949 crossref_primary_10_1016_j_is_2025_102524 crossref_primary_10_1109_TSG_2022_3177154 crossref_primary_10_1080_12460125_2022_2071404 crossref_primary_10_1007_s00202_023_01963_8 crossref_primary_10_3390_en16176203 crossref_primary_10_1109_JIOT_2024_3476268 crossref_primary_10_1109_TPWRD_2021_3102148 crossref_primary_10_1109_TPWRD_2023_3268767 crossref_primary_10_1007_s10207_023_00720_z crossref_primary_10_1016_j_ress_2025_111309 crossref_primary_10_1109_TPWRS_2022_3209343 crossref_primary_10_1016_j_epsr_2023_109553 crossref_primary_10_1016_j_ipm_2023_103306
Cites_doi	10.1109/EEEIC.2016.7555623 10.1109/TSG.2018.2816027 10.1109/TII.2017.2772081 10.1109/TII.2018.2855428 10.1109/TII.2020.2976752 10.1007/s11227-018-2674-1 10.1109/TPWRS.2020.2986019 10.1109/TSG.2014.2302016 10.3390/make1030054 10.1016/j.ijepes.2020.106255 10.1109/TII.2018.2850930 10.1111/coin.12146 10.1145/3146347.3146356 10.1109/TSG.2011.2106521 10.1080/10618600.2019.1617160 10.3390/s20051261 10.1145/3152494.3152501 10.1109/TSG.2016.2559444 10.1109/AERO.2005.1559688 10.1016/j.neucom.2017.04.070 10.1109/TPWRD.2014.2334471 10.1109/PESGM.2018.8586320 10.1145/2934664 10.1109/TIA.2019.2928500 10.1007/978-3-319-17701-4_23 10.1109/TPWRD.2016.2520958
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 7TB 8FD FR3 KR7 L7M
DOI	10.1109/TSG.2021.3054375
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 Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database Civil Engineering Abstracts Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Civil Engineering Abstracts Engineering Research Database Technology Research Database Mechanical & Transportation Engineering Abstracts Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Civil Engineering Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1949-3061
EndPage	3580
ExternalDocumentID	10_1109_TSG_2021_3054375 9335975
Genre	orig-research
GrantInformation_xml	– fundername: U.S. NSF FW-HTF grantid: 1840192 funderid: 10.13039/100000001 – fundername: Siemens Corporate Research (SCR) funderid: 10.13039/501100004830 – fundername: PNNL Data-Model Convergence initiative
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ IFIPE IPLJI JAVBF M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION 7SP 7TB 8FD FR3 KR7 L7M
ID	FETCH-LOGICAL-c291t-1c738cc4eb232d09c7e9f30dd00dfdf93048a057fa2d6721ee768e978545529a3
IEDL.DBID	RIE
ISICitedReferencesCount	47
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000663539700069&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1949-3053
IngestDate	Mon Jun 30 09:37:38 EDT 2025 Tue Nov 18 22:18:35 EST 2025 Sat Nov 29 03:45:58 EST 2025 Wed Aug 27 02:50:51 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-1c738cc4eb232d09c7e9f30dd00dfdf93048a057fa2d6721ee768e978545529a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-3518-8018
PQID	2542500249
PQPubID	2040408
PageCount	11
ParticipantIDs	proquest_journals_2542500249 crossref_primary_10_1109_TSG_2021_3054375 crossref_citationtrail_10_1109_TSG_2021_3054375 ieee_primary_9335975
PublicationCentury	2000
PublicationDate	2021-07-01
PublicationDateYYYYMMDD	2021-07-01
PublicationDate_xml	– month: 07 year: 2021 text: 2021-07-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE transactions on smart grid
PublicationTitleAbbrev	TSG
PublicationYear	2021
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 ref12 ref15 ester (ref10) 1996; 96 ref14 ref31 ref30 ref11 ref32 ref2 ref1 bertsekas (ref24) 1989; 23 ref16 ref19 ref18 emmert-streib (ref28) 2019; 1 ikeda (ref17) 2018 ref23 ref26 ref25 ref20 ref22 ref21 ref8 ref9 ref4 pedregosa (ref27) 2011; 12 ref3 ref6 zinkevich (ref29) 2010 ref5 zhou (ref7) 2009; 5
References_xml	– volume: 12 start-page: 2825 year: 2011 ident: ref27 article-title: Scikit-learn: Machine learning in Python publication-title: J Mach Learn Res – ident: ref25 doi: 10.1109/EEEIC.2016.7555623 – ident: ref2 doi: 10.1109/TSG.2018.2816027 – start-page: 2595 year: 2010 ident: ref29 article-title: Parallelized stochastic gradient descent publication-title: Advances in neural information processing systems – ident: ref5 doi: 10.1109/TII.2017.2772081 – ident: ref23 doi: 10.1109/TII.2018.2855428 – ident: ref12 doi: 10.1109/TII.2020.2976752 – ident: ref13 doi: 10.1007/s11227-018-2674-1 – ident: ref6 doi: 10.1109/TPWRS.2020.2986019 – ident: ref1 doi: 10.1109/TSG.2014.2302016 – volume: 1 start-page: 945 year: 2019 ident: ref28 article-title: Understanding statistical hypothesis testing: The logic of statistical inference publication-title: Machine Learning and Knowledge Extraction doi: 10.3390/make1030054 – ident: ref32 doi: 10.1016/j.ijepes.2020.106255 – ident: ref18 doi: 10.1109/TII.2018.2850930 – ident: ref15 doi: 10.1111/coin.12146 – ident: ref30 doi: 10.1145/3146347.3146356 – ident: ref19 doi: 10.1109/TSG.2011.2106521 – volume: 96 start-page: 226 year: 1996 ident: ref10 article-title: A density-based algorithm for discovering clusters in large spatial databases with noise publication-title: Proc 2nd Int Conf Knowl Discov Data Min (KDD) – volume: 5 start-page: 1697 year: 2009 ident: ref7 article-title: Anomaly detection over concept drifting data streams publication-title: J Comput Inf Syst – ident: ref14 doi: 10.1080/10618600.2019.1617160 – volume: 23 year: 1989 ident: ref24 publication-title: Parallel and Distributed Computation Numerical Methods – year: 2018 ident: ref17 article-title: Human-assisted online anomaly detection with normal outlier retraining publication-title: Proc ACM SIGKDD Workshop – ident: ref8 doi: 10.3390/s20051261 – ident: ref9 doi: 10.1145/3152494.3152501 – ident: ref22 doi: 10.1109/TSG.2016.2559444 – ident: ref11 doi: 10.1109/AERO.2005.1559688 – ident: ref16 doi: 10.1016/j.neucom.2017.04.070 – ident: ref21 doi: 10.1109/TPWRD.2014.2334471 – ident: ref3 doi: 10.1109/PESGM.2018.8586320 – ident: ref26 doi: 10.1145/2934664 – ident: ref4 doi: 10.1109/TIA.2019.2928500 – ident: ref31 doi: 10.1007/978-3-319-17701-4_23 – ident: ref20 doi: 10.1109/TPWRD.2016.2520958
SSID	ssj0000333629
Score	2.538643
Snippet	With ongoing automation and digitization of the electric power system, several Phasor Measurement Units (PMUs) have been deployed for monitoring and control....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	3570
SubjectTerms	Algorithms Anomalies anomaly and event classification Anomaly detection Classification Data transmission Deep learning Distance learning Distributed generation Electric power grids Electric power systems Electrical loads Electricity distribution Energy sources Fault detection Heuristic algorithms Localization Machine learning Measuring instruments Multivariate analysis Online instruction Phasor measurement units Phasors Power system dynamics Real time Real-time systems Stress concentration Switching Training
Title	Anomaly Detection, Localization and Classification Using Drifting Synchrophasor Data Streams
URI	https://ieeexplore.ieee.org/document/9335975 https://www.proquest.com/docview/2542500249
Volume	12
WOSCitedRecordID	wos000663539700069&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 Electronic Library (IEL) customDbUrl: eissn: 1949-3061 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000333629 issn: 1949-3053 databaseCode: RIE dateStart: 20100101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4kEPvqpYrZKDF6HbppvuI0exVg9ShFboQVjSPLDQbqXdCv33TrLbUlAEb0tIwpJJMvNlvpkBuA2lr5kygSfC2L5WdbjH6RgvwzCSQqMKV8a4YhNRvx-PRvy1BI1tLIzW2pHPdNN-Ol--msuVfSprIfhG-zcoQzmKwjxWa_ueQhnDu5g7J3LHuvMDtvFKUt4aDp4QC_rtJrZ3mCUV7mghV1blx13sFEzv6H-_dgyHhSFJ7nPJn0BJp6dwsJNesArviO1nYromXZ05xlXaIC9WdxWxl0SkiriqmJYvlDc5CgHpLibG8qHJYJ1KW0jhQyznC9IVmSDWjy1myzN46z0OH569opqCJ33ezry2jFgsZQehNEqAchlpbhhVilJllOEMz7JA680IX4WIC7VGJKIRZKKNFfhcsHOopPNUXwBhDPW6pFxISXE-E7NQj2OjmBmPhQxMDVqb1U1kkWrcVryYJg5yUJ6gPBIrj6SQRw3utiM-8zQbf_St2vXf9iuWvgb1jQCT4hwuE4S_aOPZtIiXv4-6gn07d07ArUMlW6z0NezJr2yyXNy4LfYNRCjPKg
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_mFNQHv6Y4P_Pgi2Bd1rRd8yjOqTiH4AQfhJLlAwfaydoJ---9pN0QFMG3EpK25JLc_e5-uQM4iaSvmTKhJ6LYeqsC7nE6wMMwakmhUYUrY1yxiVavFz8_84cKnM3vwmitHflMn9tHF8tXIzmxrrIGgm-0f8MFWAyDwKfFba25R4Uyhqcxd2HkwAb0QzaLS1Le6D9eIxr0m-fYHjBLK_ymh1xhlR-nsVMxnfX__dwGrJWmJLkoZL8JFZ1uweq3BIM1eEF0_y7epqStc8e5Ss9I12qv8vYlEakiri6mZQwVTY5EQNrjobGMaPI4TaUtpfAqstGYtEUuiI1ki_dsG546V_3LG6-sp-BJnzdzrylbLJYyQDCNMqBctjQ3jCpFqTLKcIa7WaD9ZoSvIkSGWiMW0Qgz0coKfS7YDlTTUap3gTCGml1SLqSk-D4Ts0gPYqOYGQyEDE0dGrPZTWSZbNzWvHhLHOigPEF5JFYeSSmPOpzOR3wUiTb-6Fuz8z_vV059HQ5mAkzKnZglCIDRyrOJEfd-H3UMyzf9-27Sve3d7cOK_U5Bxz2Aaj6e6ENYkp_5MBsfueX2BTM-0nE
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+Detection%2C+Localization+and+Classification+Using+Drifting+Synchrophasor+Data+Streams&rft.jtitle=IEEE+transactions+on+smart+grid&rft.au=Ahmed%2C+A.&rft.au=Sajan%2C+K.+S.&rft.au=Srivastava%2C+A.&rft.au=Wu%2C+Y.&rft.date=2021-07-01&rft.issn=1949-3053&rft.eissn=1949-3061&rft.volume=12&rft.issue=4&rft.spage=3570&rft.epage=3580&rft_id=info:doi/10.1109%2FTSG.2021.3054375&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSG_2021_3054375
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1949-3053&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1949-3053&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1949-3053&client=summon