Power System Anomaly Detection Via Ensemble of Encoder and Decoder Networks

Hacking and false data injection from adversaries can threaten power grids' normal operations and cause significant economic loss. Anomaly detection in power grids aims to detect and discriminate anomalies caused by the cyberattack against the power system which is essential for keeping power g...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 IEEE Electrical Power and Energy Conference (EPEC) s. 116 - 122
Hlavní autoři: Sun, Xijuan, Wu, Di, Zinflou, Arnaud, Boulet, Benoit
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 05.12.2022
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Hacking and false data injection from adversaries can threaten power grids' normal operations and cause significant economic loss. Anomaly detection in power grids aims to detect and discriminate anomalies caused by the cyberattack against the power system which is essential for keeping power grids working properly and efficiently. Different types of methods have been applied for anomaly detection such as statistical methods and machine learning-based methods. For machine learning-based methods, we usually need to model the distribution of normal data. In this work, we propose a novel anomaly detection method by modeling the data distribution of normal samples via multiple encoders and decoders. Specifically, the proposed method maps input samples into a latent space and then reconstructs output samples from latent vectors. The extra encoder finally maps reconstructed samples into the latent representations. During the training phase, parameters are optimized by minimizing reconstruction loss and encoding loss. Furthermore, training samples are re-weighted to focus more on missed correlations among features of normal data. Experiment results on network intrusion and power system datasets demonstrate the effectiveness of our proposed method, where our model consistently outperforms all baselines.
AbstractList Hacking and false data injection from adversaries can threaten power grids' normal operations and cause significant economic loss. Anomaly detection in power grids aims to detect and discriminate anomalies caused by the cyberattack against the power system which is essential for keeping power grids working properly and efficiently. Different types of methods have been applied for anomaly detection such as statistical methods and machine learning-based methods. For machine learning-based methods, we usually need to model the distribution of normal data. In this work, we propose a novel anomaly detection method by modeling the data distribution of normal samples via multiple encoders and decoders. Specifically, the proposed method maps input samples into a latent space and then reconstructs output samples from latent vectors. The extra encoder finally maps reconstructed samples into the latent representations. During the training phase, parameters are optimized by minimizing reconstruction loss and encoding loss. Furthermore, training samples are re-weighted to focus more on missed correlations among features of normal data. Experiment results on network intrusion and power system datasets demonstrate the effectiveness of our proposed method, where our model consistently outperforms all baselines.
Author Zinflou, Arnaud
Sun, Xijuan
Boulet, Benoit
Wu, Di
Author_xml – sequence: 1
  givenname: Xijuan
  surname: Sun
  fullname: Sun, Xijuan
  email: xijuan.sun@mail.mcgill.ca
  organization: McGill University,Department of Electrical and Computer Engineering,Montreal,Canada
– sequence: 2
  givenname: Di
  surname: Wu
  fullname: Wu, Di
  email: di.wu5@mcgill.ca
  organization: McGill University,Department of Electrical and Computer Engineering,Montreal,Canada
– sequence: 3
  givenname: Arnaud
  surname: Zinflou
  fullname: Zinflou, Arnaud
  email: zinflou.arnaud@hydroquebec.com
  organization: Hydro-Québec's research institute,Montreal,Canada
– sequence: 4
  givenname: Benoit
  surname: Boulet
  fullname: Boulet, Benoit
  email: benoit.boulet@mcgill.ca
  organization: McGill University,Department of Electrical and Computer Engineering,Montreal,Canada
BookMark eNo1T81KxDAYjKAHd_UNBPMCrfmSNE2OS62uuOiCP3hb0uQLFNtE2sLSt7ewOpeZgZmBWZHzmCIScgssB2Dmrt7XVaEMEzlnnOfAFvCCnZEVKFVIJUB_XZLnfTriQN_mccKebmLqbTfTe5zQTW2K9LO1tI4j9k2HNIVFu-SXgo1-SZ30C07HNHyPV-Qi2G7E6z9ek4-H-r3aZrvXx6dqs8tazuSUGY0QrIZG8eCcKr02HDxjaLyExZcOG3SNFaW0pXRKNEoYpwN4lA4cijW5Oe22iHj4GdreDvPh_6D4BUqDS6g
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/EPEC56903.2022.10000250
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 166546318X
9781665463188
EndPage 122
ExternalDocumentID 10000250
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i204t-98e1fa81b62fcc67d8921d00e9d41c677cebecba374a74c63b639c8f1de4c1ce3
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000946642000020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:13:56 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-98e1fa81b62fcc67d8921d00e9d41c677cebecba374a74c63b639c8f1de4c1ce3
PageCount 7
ParticipantIDs ieee_primary_10000250
PublicationCentury 2000
PublicationDate 2022-Dec.-5
PublicationDateYYYYMMDD 2022-12-05
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-Dec.-5
  day: 05
PublicationDecade 2020
PublicationTitle 2022 IEEE Electrical Power and Energy Conference (EPEC)
PublicationTitleAbbrev EPEC
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8299341
Snippet Hacking and false data injection from adversaries can threaten power grids' normal operations and cause significant economic loss. Anomaly detection in power...
SourceID ieee
SourceType Publisher
StartPage 116
SubjectTerms Anomaly detection
Correlation
Data models
Decoding
encoder and decoder
ensemble
Feature extraction
Learning systems
one-class classification
power system
Time series analysis
Training
Title Power System Anomaly Detection Via Ensemble of Encoder and Decoder Networks
URI https://ieeexplore.ieee.org/document/10000250
WOSCitedRecordID wos000946642000020&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1aPHhSseI3OXhNu_losjnXLYKw7EGlt5JNJlBot9JuBf-9SbZVPHjwNllCFmYOk5e8l4fQg-PCZpZ7ImvJiXDakgCbNbHRc7pmcZfvk9mEKst8OtXVTqyetDAAkMhnMIhhust3K7uNR2XDdBbNIkI_VEp2Yq0dZ4tmelhUxXgU0B4PsI-xwX72L9-U1DYmJ__84Snq_wjwcPXdWs7QATTn6LmKjma4e2McB9y-NItP_AhtYlM1-G1ucNFsYFkvAK98iKNefY1N48KsLi471vemj14nxcv4iey8EMicZaIlOgfqTdhjSuatlcrlmlGXZaCdoGGsbKxGbbgSRgkreUi9trmnDoSlFvgF6jWrBi4RDg1Je6qdCTUSuRRhVVMzBiNXO8FNdoX6MROz9-65i9k-Cdd_fL9BxzHfieMxukW9dr2FO3RkP9r5Zn2fivQFPamUBQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1SBT2pWPHbHLxuu_nYj5zrlkrrsocqvZVsMoFCuy3tVvDfm2RbxYMHb5MlZGHmMHnJe3kIPWnGVaiYCeIyZgHXQgUWNotAOc_pkrpdvvFmE0mep5OJKHZida-FAQBPPoOOC_1dvl6qrTsq6_qzaOoQ-mHEOQ0budaOtUVC0c2KrBdZvMcs8KO0s5__yznFN47-6T9_eYbaPxI8XHw3l3N0ANUFGhbO0ww3r4xji9wXcv6Jn6H2fKoKv88kzqoNLMo54KWxsVOsr7GstJ3VxHnD-9600Vs_G_cGwc4NIZjRkNeBSIEYaXeZMTVKxYlOBSU6DEFoTuw4Ua4epWQJlwlXMbPJFyo1RANXRAG7RK1qWcEVwrYlCUOElrZKPI25XVWWlEKkS82ZDK9R22ViumoevJjuk3Dzx_dHdDwYv46mo5d8eItOXO494yO6Q616vYV7dKQ-6tlm_eAL9gUg8pdM
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%3Abook&rft.genre=proceeding&rft.title=2022+IEEE+Electrical+Power+and+Energy+Conference+%28EPEC%29&rft.atitle=Power+System+Anomaly+Detection+Via+Ensemble+of+Encoder+and+Decoder+Networks&rft.au=Sun%2C+Xijuan&rft.au=Wu%2C+Di&rft.au=Zinflou%2C+Arnaud&rft.au=Boulet%2C+Benoit&rft.date=2022-12-05&rft.pub=IEEE&rft.spage=116&rft.epage=122&rft_id=info:doi/10.1109%2FEPEC56903.2022.10000250&rft.externalDocID=10000250