Toward Automated Anomaly Identification in Large-Scale Systems
When a system fails to function properly, health-related data are collected for troubleshooting. However, it is challenging to effectively identify anomalies from the voluminous amount of noisy, high-dimensional data. The traditional manual approach is time-consuming, error-prone, and even worse, no...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on parallel and distributed systems 2010-02, Vol.21 (2), p.174-187 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 187 |
---|---|
container_issue | 2 |
container_start_page | 174 |
container_title | IEEE transactions on parallel and distributed systems |
container_volume | 21 |
creator | Lan, Zhiling Zheng, Ziming Li, Yawei |
description | When a system fails to function properly, health-related data are collected for troubleshooting. However, it is challenging to effectively identify anomalies from the voluminous amount of noisy, high-dimensional data. The traditional manual approach is time-consuming, error-prone, and even worse, not scalable. In this paper, we present an automated mechanism for node-level anomaly identification in large-scale systems. A set of techniques is presented to automatically analyze collected data: data transformation to construct a uniform data format for data analysis, feature extraction to reduce data size, and unsupervised learning to detect the nodes acting differently from others. Moreover, we compare two techniques, principal component analysis (PCA) and independent component analysis (ICA), for feature extraction. We evaluate our prototype implementation by injecting a variety of faults into a production system at NCSA. The results show that our mechanism, in particular, the one using ICA-based feature extraction, can effectively identify faulty nodes with high accuracy and low computation overhead. |
doi_str_mv | 10.1109/TPDS.2009.52 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_912031664</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4815224</ieee_id><sourcerecordid>2543477621</sourcerecordid><originalsourceid>FETCH-LOGICAL-c352t-aa791faeed728daa9d3f93138da63ca843c64a30d8f599f2baecd24066396a623</originalsourceid><addsrcrecordid>eNpdkEtLw0AQgBdRsFZv3rwEL15M3Xd2L0Kpr0JBofW8jJuJpORRdxOk_96EigdP8x0-ZoaPkEtGZ4xRe7d5e1jPOKV2pvgRmTClTMqZEccDU6lSy5k9JWcxbillUlE5Ifeb9htCnsz7rq2hw4GaAap9ssyx6cqi9NCVbZOUTbKC8Inp2kOFyXofO6zjOTkpoIp48Tun5P3pcbN4SVevz8vFfJV6oXiXAmSWFYCYZ9zkADYXhRVMDKyFByOF1xIEzU2hrC34B6DPuaRaC6tBczElN4e9u9B-9Rg7V5fRY1VBg20fnckU5SyzajCv_5nbtg_N8JyzjFPBtJaDdHuQfGhjDFi4XShrCHvHqBtTujGlG1M6NV6_OuglIv6p0jDFuRQ_sO1ueg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>912031664</pqid></control><display><type>article</type><title>Toward Automated Anomaly Identification in Large-Scale Systems</title><source>IEEE Xplore</source><creator>Lan, Zhiling ; Zheng, Ziming ; Li, Yawei</creator><creatorcontrib>Lan, Zhiling ; Zheng, Ziming ; Li, Yawei</creatorcontrib><description>When a system fails to function properly, health-related data are collected for troubleshooting. However, it is challenging to effectively identify anomalies from the voluminous amount of noisy, high-dimensional data. The traditional manual approach is time-consuming, error-prone, and even worse, not scalable. In this paper, we present an automated mechanism for node-level anomaly identification in large-scale systems. A set of techniques is presented to automatically analyze collected data: data transformation to construct a uniform data format for data analysis, feature extraction to reduce data size, and unsupervised learning to detect the nodes acting differently from others. Moreover, we compare two techniques, principal component analysis (PCA) and independent component analysis (ICA), for feature extraction. We evaluate our prototype implementation by injecting a variety of faults into a production system at NCSA. The results show that our mechanism, in particular, the one using ICA-based feature extraction, can effectively identify faulty nodes with high accuracy and low computation overhead.</description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/TPDS.2009.52</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Anomalies ; Anomaly identification ; Application software ; Automated ; Automation ; Computer errors ; Computer networks ; Data analysis ; Fault diagnosis ; Feature extraction ; Format ; Independent component analysis ; Large-scale systems ; outlier detection ; Principal component analysis ; Principal components analysis ; Production systems ; Studies ; Transformations ; Unsupervised learning</subject><ispartof>IEEE transactions on parallel and distributed systems, 2010-02, Vol.21 (2), p.174-187</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Feb 2010</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c352t-aa791faeed728daa9d3f93138da63ca843c64a30d8f599f2baecd24066396a623</citedby><cites>FETCH-LOGICAL-c352t-aa791faeed728daa9d3f93138da63ca843c64a30d8f599f2baecd24066396a623</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4815224$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4815224$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Lan, Zhiling</creatorcontrib><creatorcontrib>Zheng, Ziming</creatorcontrib><creatorcontrib>Li, Yawei</creatorcontrib><title>Toward Automated Anomaly Identification in Large-Scale Systems</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>When a system fails to function properly, health-related data are collected for troubleshooting. However, it is challenging to effectively identify anomalies from the voluminous amount of noisy, high-dimensional data. The traditional manual approach is time-consuming, error-prone, and even worse, not scalable. In this paper, we present an automated mechanism for node-level anomaly identification in large-scale systems. A set of techniques is presented to automatically analyze collected data: data transformation to construct a uniform data format for data analysis, feature extraction to reduce data size, and unsupervised learning to detect the nodes acting differently from others. Moreover, we compare two techniques, principal component analysis (PCA) and independent component analysis (ICA), for feature extraction. We evaluate our prototype implementation by injecting a variety of faults into a production system at NCSA. The results show that our mechanism, in particular, the one using ICA-based feature extraction, can effectively identify faulty nodes with high accuracy and low computation overhead.</description><subject>Anomalies</subject><subject>Anomaly identification</subject><subject>Application software</subject><subject>Automated</subject><subject>Automation</subject><subject>Computer errors</subject><subject>Computer networks</subject><subject>Data analysis</subject><subject>Fault diagnosis</subject><subject>Feature extraction</subject><subject>Format</subject><subject>Independent component analysis</subject><subject>Large-scale systems</subject><subject>outlier detection</subject><subject>Principal component analysis</subject><subject>Principal components analysis</subject><subject>Production systems</subject><subject>Studies</subject><subject>Transformations</subject><subject>Unsupervised learning</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkEtLw0AQgBdRsFZv3rwEL15M3Xd2L0Kpr0JBofW8jJuJpORRdxOk_96EigdP8x0-ZoaPkEtGZ4xRe7d5e1jPOKV2pvgRmTClTMqZEccDU6lSy5k9JWcxbillUlE5Ifeb9htCnsz7rq2hw4GaAap9ssyx6cqi9NCVbZOUTbKC8Inp2kOFyXofO6zjOTkpoIp48Tun5P3pcbN4SVevz8vFfJV6oXiXAmSWFYCYZ9zkADYXhRVMDKyFByOF1xIEzU2hrC34B6DPuaRaC6tBczElN4e9u9B-9Rg7V5fRY1VBg20fnckU5SyzajCv_5nbtg_N8JyzjFPBtJaDdHuQfGhjDFi4XShrCHvHqBtTujGlG1M6NV6_OuglIv6p0jDFuRQ_sO1ueg</recordid><startdate>201002</startdate><enddate>201002</enddate><creator>Lan, Zhiling</creator><creator>Zheng, Ziming</creator><creator>Li, Yawei</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>201002</creationdate><title>Toward Automated Anomaly Identification in Large-Scale Systems</title><author>Lan, Zhiling ; Zheng, Ziming ; Li, Yawei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c352t-aa791faeed728daa9d3f93138da63ca843c64a30d8f599f2baecd24066396a623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Anomalies</topic><topic>Anomaly identification</topic><topic>Application software</topic><topic>Automated</topic><topic>Automation</topic><topic>Computer errors</topic><topic>Computer networks</topic><topic>Data analysis</topic><topic>Fault diagnosis</topic><topic>Feature extraction</topic><topic>Format</topic><topic>Independent component analysis</topic><topic>Large-scale systems</topic><topic>outlier detection</topic><topic>Principal component analysis</topic><topic>Principal components analysis</topic><topic>Production systems</topic><topic>Studies</topic><topic>Transformations</topic><topic>Unsupervised learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lan, Zhiling</creatorcontrib><creatorcontrib>Zheng, Ziming</creatorcontrib><creatorcontrib>Li, Yawei</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lan, Zhiling</au><au>Zheng, Ziming</au><au>Li, Yawei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Toward Automated Anomaly Identification in Large-Scale Systems</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>2010-02</date><risdate>2010</risdate><volume>21</volume><issue>2</issue><spage>174</spage><epage>187</epage><pages>174-187</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>When a system fails to function properly, health-related data are collected for troubleshooting. However, it is challenging to effectively identify anomalies from the voluminous amount of noisy, high-dimensional data. The traditional manual approach is time-consuming, error-prone, and even worse, not scalable. In this paper, we present an automated mechanism for node-level anomaly identification in large-scale systems. A set of techniques is presented to automatically analyze collected data: data transformation to construct a uniform data format for data analysis, feature extraction to reduce data size, and unsupervised learning to detect the nodes acting differently from others. Moreover, we compare two techniques, principal component analysis (PCA) and independent component analysis (ICA), for feature extraction. We evaluate our prototype implementation by injecting a variety of faults into a production system at NCSA. The results show that our mechanism, in particular, the one using ICA-based feature extraction, can effectively identify faulty nodes with high accuracy and low computation overhead.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TPDS.2009.52</doi><tpages>14</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1045-9219 |
ispartof | IEEE transactions on parallel and distributed systems, 2010-02, Vol.21 (2), p.174-187 |
issn | 1045-9219 1558-2183 |
language | eng |
recordid | cdi_proquest_journals_912031664 |
source | IEEE Xplore |
subjects | Anomalies Anomaly identification Application software Automated Automation Computer errors Computer networks Data analysis Fault diagnosis Feature extraction Format Independent component analysis Large-scale systems outlier detection Principal component analysis Principal components analysis Production systems Studies Transformations Unsupervised learning |
title | Toward Automated Anomaly Identification in Large-Scale Systems |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A09%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Toward%20Automated%20Anomaly%20Identification%20in%20Large-Scale%20Systems&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Lan,%20Zhiling&rft.date=2010-02&rft.volume=21&rft.issue=2&rft.spage=174&rft.epage=187&rft.pages=174-187&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/TPDS.2009.52&rft_dat=%3Cproquest_RIE%3E2543477621%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=912031664&rft_id=info:pmid/&rft_ieee_id=4815224&rfr_iscdi=true |