{"id":"https://openalex.org/W2148508494","doi":"https://doi.org/10.1145/1362622.1362678","title":"Exploring event correlation for failure prediction in coalitions of clusters","display_name":"Exploring event correlation for failure prediction in coalitions of clusters","publication_year":2007,"publication_date":"2007-11-10","ids":{"openalex":"https://openalex.org/W2148508494","doi":"https://doi.org/10.1145/1362622.1362678","mag":"2148508494"},"language":"en","primary_location":{"id":"doi:10.1145/1362622.1362678","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1362622.1362678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM/IEEE conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082758762","display_name":"Song Fu","orcid":"https://orcid.org/0000-0002-7705-0829"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Fu","raw_affiliation_strings":["Wayne State University, Detroit, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Zhong Xu","raw_affiliation_strings":["Wayne State University, Detroit, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":11.1242,"has_fulltext":false,"cited_by_count":180,"citation_normalized_percentile":{"value":0.99132166,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111424207687378},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5838112831115723},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5831815600395203},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5324313044548035},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4808152914047241},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.469513863325119},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4496583640575409},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.42259305715560913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36019647121429443},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13229885697364807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1203223466873169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111424207687378},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5838112831115723},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5831815600395203},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5324313044548035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4808152914047241},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.469513863325119},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4496583640575409},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.42259305715560913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36019647121429443},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13229885697364807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1203223466873169},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1362622.1362678","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1362622.1362678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM/IEEE conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.122.8727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.122.8727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ece.eng.wayne.edu/~czxu/paper/SC07-failure.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.325.2689","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.325.2689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unt.edu/~song/Publications/FP-sc07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6444824284","display_name":null,"funder_award_id":"CCF-0611750DMS-0624849CNS-0702488CRI-0708232","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W424839606","https://openalex.org/W1527235902","https://openalex.org/W1558516248","https://openalex.org/W1577857692","https://openalex.org/W1767150602","https://openalex.org/W1945970356","https://openalex.org/W1969359541","https://openalex.org/W1980627207","https://openalex.org/W1985699615","https://openalex.org/W1990911977","https://openalex.org/W2006075444","https://openalex.org/W2053691501","https://openalex.org/W2068171717","https://openalex.org/W2095104918","https://openalex.org/W2096121981","https://openalex.org/W2103759606","https://openalex.org/W2114739461","https://openalex.org/W2121098551","https://openalex.org/W2123486598","https://openalex.org/W2127467730","https://openalex.org/W2130016203","https://openalex.org/W2140991542","https://openalex.org/W2143220335","https://openalex.org/W2145227912","https://openalex.org/W2157500273","https://openalex.org/W2158016161","https://openalex.org/W2158692258","https://openalex.org/W2158848208","https://openalex.org/W2158907675","https://openalex.org/W2160821994","https://openalex.org/W2164136293","https://openalex.org/W2164713843","https://openalex.org/W2405200838","https://openalex.org/W2473052521","https://openalex.org/W4235660274","https://openalex.org/W6681043256","https://openalex.org/W6681723757"],"related_works":["https://openalex.org/W2788344745","https://openalex.org/W2062336688","https://openalex.org/W2910677864","https://openalex.org/W2046078371","https://openalex.org/W2383820648","https://openalex.org/W4245445763","https://openalex.org/W3162209258","https://openalex.org/W2054128830","https://openalex.org/W4319736142","https://openalex.org/W2085143107"],"abstract_inverted_index":{"In":[0,35],"large-scale":[1],"networked":[2],"computing":[3],"systems,":[4],"component":[5],"failures":[6,108],"become":[7],"norms":[8],"instead":[9],"of":[10,67,98,113,120,126],"exceptions.":[11],"Failure":[12,22,99],"prediction":[13,94,125,137,156,164],"is":[14],"a":[15,40,55,92],"crucial":[16],"technique":[17],"for":[18],"self-managing":[19],"resource":[20],"burdens.":[21],"events":[23,80],"in":[24,30,122,138,154,162],"coalition":[25,142],"systems":[26],"exhibit":[27],"strong":[28],"correlations":[29,73,84,106],"time":[31,167],"and":[32,54,85,109,135,157],"space":[33],"domain.":[34],"this":[36],"paper,":[37],"we":[38],"develop":[39],"spherical":[41],"covariance":[42],"model":[43,57],"with":[44],"an":[45,139],"adjustable":[46],"timescale":[47],"parameter":[48],"to":[49,58,70,171],"quantify":[50],"the":[51,65,111,118,130,147,166],"temporal":[52],"correlation":[53],"stochastic":[56],"describe":[59],"spatial":[60],"correlation.":[61],"We":[62,77,90,116],"further":[63],"utilize":[64],"information":[66],"application":[68],"allocation":[69],"discover":[71],"more":[72,150,158],"among":[74,107],"failure":[75,79,93,127],"instances.":[76,115],"cluster":[78],"based":[81],"on":[82],"their":[83,87],"predict":[86],"future":[88,114],"occurrences.":[89],"implemented":[91],"framework,":[95],"called":[96],"PREdictor":[97],"Events":[100],"Correlated":[101],"Temporal-Spatially":[102],"(hPREFECTs),":[103],"which":[104],"explores":[105],"forecasts":[110],"time-between-failure":[112],"evaluate":[117],"performance":[119],"hPREFECTs":[121],"both":[123],"offline":[124,155],"by":[128],"using":[129],"Los":[131],"Alamos":[132],"HPC":[133],"traces":[134],"online":[136,163],"institute-wide":[140],"clusters":[141],"environment.":[143],"Experimental":[144],"results":[145],"show":[146],"system":[148],"achieves":[149],"than":[151,159],"76%":[152],"accuracy":[153,161],"70%":[160],"during":[165],"from":[168],"May":[169],"2006":[170],"April":[172],"2007.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":21}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}