{"id":"https://openalex.org/W1589384255","doi":"https://doi.org/10.1109/hipc.2014.7116903","title":"Online failure prediction for HPC resources using decentralized clustering","display_name":"Online failure prediction for HPC resources using decentralized clustering","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1589384255","doi":"https://doi.org/10.1109/hipc.2014.7116903","mag":"1589384255"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2014.7116903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2014.7116903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 21st International Conference on High Performance Computing (HiPC)","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/A5067612036","display_name":"Alejandro Pel\u00e1ez-Vargas","orcid":"https://orcid.org/0000-0001-7582-2760"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Pelaez","raw_affiliation_strings":["Rutgers, The State University of New Jersey, RDI2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, RDI2","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028472141","display_name":"Andres Quiroz","orcid":"https://orcid.org/0009-0009-1449-392X"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andres Quiroz","raw_affiliation_strings":["Xerox Research, Webster, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research, Webster, NY","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064263297","display_name":"James C. Browne","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James C. Browne","raw_affiliation_strings":["University of Texas at Austin","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015074167","display_name":"Edward Chuah","orcid":"https://orcid.org/0000-0002-8659-1803"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Chuah","raw_affiliation_strings":["University of Texas at Austin","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060153432","display_name":"Manish Parashar","orcid":"https://orcid.org/0000-0003-0983-7408"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Parashar","raw_affiliation_strings":["Rutgers, The State University of New Jersey, RDI2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, RDI2","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3799,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.78706054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.823448657989502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8229629993438721},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.666954517364502},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6556112170219421},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5980350375175476},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5893732309341431},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5046452283859253},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4493551254272461},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42169368267059326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2656377851963043},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21240490674972534},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14133235812187195},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07881367206573486}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.823448657989502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229629993438721},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.666954517364502},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6556112170219421},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5980350375175476},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5893732309341431},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5046452283859253},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4493551254272461},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42169368267059326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2656377851963043},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21240490674972534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14133235812187195},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07881367206573486},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2014.7116903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2014.7116903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 21st International Conference on High Performance Computing (HiPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1592847587","https://openalex.org/W1673310716","https://openalex.org/W1971210466","https://openalex.org/W1988099502","https://openalex.org/W1995565928","https://openalex.org/W1995603189","https://openalex.org/W2011023286","https://openalex.org/W2040932846","https://openalex.org/W2053691501","https://openalex.org/W2064758237","https://openalex.org/W2106938068","https://openalex.org/W2107461003","https://openalex.org/W2107809577","https://openalex.org/W2123659430","https://openalex.org/W2142812297","https://openalex.org/W2143996186","https://openalex.org/W2152426255","https://openalex.org/W2171433864","https://openalex.org/W4250013373","https://openalex.org/W4256251415","https://openalex.org/W6637131181","https://openalex.org/W6676145519"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2151092287"],"abstract_inverted_index":{"Ensuring":[0],"high":[1,36,111],"reliability":[2],"of":[3,13,26,70,127,160,170,215],"large-scale":[4],"clusters":[5,135],"is":[6,66],"becoming":[7],"more":[8],"critical":[9],"as":[10,94,196],"the":[11,22,53,89,125,168,175,179],"size":[12],"these":[14],"machines":[15],"continues":[16],"to":[17,47,67,73,87,124,144,155,157,211],"grow,":[18],"since":[19],"this":[20,40,107,171,190],"increases":[21],"complexity":[23],"and":[24,31,83,86,113,204],"amount":[25],"interactions":[27],"between":[28,76],"different":[29],"nodes":[30],"thus":[32],"results":[33],"in":[34,45,52,106,132,147,163],"a":[35,122,138,208],"failure":[37,64,95,104],"frequency.":[38],"For":[39],"reason,":[41],"predicting":[42,128],"node":[43,84,130,161],"failures":[44,162],"order":[46],"prevent":[48],"errors":[49],"from":[50,110,178],"happening":[51],"first":[54],"place":[55],"has":[56],"become":[57],"extremely":[58],"valuable.":[59],"A":[60],"common":[61],"approach":[62,191],"for":[63,103],"prediction":[65,105],"analyze":[68],"traces":[69],"system":[71,172],"events":[72],"find":[74],"correlations":[75],"event":[77,81],"types":[78,90,159],"or":[79,91],"anomalous":[80],"patterns":[82,92],"failures,":[85],"use":[88],"identified":[93],"predictors":[96],"at":[97,116,182],"run-time.":[98],"However,":[99],"typical":[100],"centralized":[101],"solutions":[102],"manner":[108],"suffer":[109],"transmission":[112],"processing":[114],"overheads":[115],"very":[117],"large":[118,133],"scales.":[119],"We":[120,166],"present":[121],"solution":[123],"problem":[126],"compute":[129],"soft-lockups":[131],"scale":[134],"by":[136,173],"using":[137,174],"decentralized":[139],"online":[140],"clustering":[141],"algorithm":[142],"(DOC)":[143],"detect":[145],"anomalies":[146],"resource":[148],"usage":[149],"logs,":[150],"which":[151],"have":[152],"been":[153],"shown":[154],"correlate":[156],"particular":[158],"supercomputer":[164,181],"clusters.":[165],"demonstrate":[167],"effectiveness":[169],"monitoring":[176],"logs":[177],"Ranger":[180],"Texas":[183],"Advanced":[184],"Computing":[185],"Center.":[186],"Experiments":[187],"shows":[188],"that":[189],"can":[192],"achieve":[193],"similar":[194],"accuracy":[195],"other":[197],"related":[198],"approaches,":[199],"while":[200],"maintaining":[201],"low":[202],"RAM":[203],"bandwidth":[205],"usage,":[206],"with":[207],"runtime":[209],"impact":[210],"current":[212],"running":[213],"applications":[214],"less":[216],"than":[217],"2%.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}