{"id":"https://openalex.org/W1983444731","doi":"https://doi.org/10.1177/1094342013488258","title":"Failure prediction for HPC systems and applications","display_name":"Failure prediction for HPC systems and applications","publication_year":2013,"publication_date":"2013-07-03","ids":{"openalex":"https://openalex.org/W1983444731","doi":"https://doi.org/10.1177/1094342013488258","mag":"1983444731"},"language":"en","primary_location":{"id":"doi:10.1177/1094342013488258","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013488258","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","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/A5021627261","display_name":"Ana Gainaru","orcid":"https://orcid.org/0000-0002-1375-9468"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ana Gainaru","raw_affiliation_strings":["National Centre for Supercomputing Applications, Urbana, IL, USA","University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"National Centre for Supercomputing Applications, Urbana, IL, USA","institution_ids":["https://openalex.org/I4210135837"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["INRIA, Rocquencourt, Le Chesnay Cedex, France","University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"INRIA, Rocquencourt, Le Chesnay Cedex, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041731995","display_name":"Marc Snir","orcid":"https://orcid.org/0000-0002-3504-2468"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Snir","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110595734","display_name":"William Kramer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Kramer","raw_affiliation_strings":["National Centre for Supercomputing Applications, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"National Centre for Supercomputing Applications, Urbana, IL, USA","institution_ids":["https://openalex.org/I4210135837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021627261"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"],"apc_list":null,"apc_paid":null,"fwci":1.8123,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.86144484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"3","first_page":"273","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9898999929428101,"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/petascale-computing","display_name":"Petascale computing","score":0.8569790720939636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8195786476135254},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6089111566543579},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.586055338382721},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5732391476631165},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.528567373752594},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.46687644720077515},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.46096962690353394},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44225138425827026},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4409673810005188},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42123791575431824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3516997694969177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.11963322758674622},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09235042333602905}],"concepts":[{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.8569790720939636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195786476135254},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6089111566543579},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.586055338382721},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5732391476631165},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.528567373752594},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.46687644720077515},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.46096962690353394},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44225138425827026},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4409673810005188},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42123791575431824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3516997694969177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.11963322758674622},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09235042333602905},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342013488258","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013488258","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W97807250","https://openalex.org/W191651381","https://openalex.org/W1507834464","https://openalex.org/W1515805777","https://openalex.org/W1581005283","https://openalex.org/W1610340100","https://openalex.org/W1923313248","https://openalex.org/W1963705790","https://openalex.org/W1981432246","https://openalex.org/W1988099502","https://openalex.org/W1995058807","https://openalex.org/W2032467893","https://openalex.org/W2040352153","https://openalex.org/W2044300056","https://openalex.org/W2047111942","https://openalex.org/W2061156425","https://openalex.org/W2081235423","https://openalex.org/W2095157729","https://openalex.org/W2107814012","https://openalex.org/W2111038504","https://openalex.org/W2114554028","https://openalex.org/W2115711419","https://openalex.org/W2119343454","https://openalex.org/W2120591095","https://openalex.org/W2136797898","https://openalex.org/W2137512117","https://openalex.org/W2141676918","https://openalex.org/W2142812297","https://openalex.org/W2143158360","https://openalex.org/W2147921378","https://openalex.org/W2153242493","https://openalex.org/W2155043308","https://openalex.org/W2155204206","https://openalex.org/W2158907675","https://openalex.org/W2159963962","https://openalex.org/W2164463086","https://openalex.org/W2263738050","https://openalex.org/W2292044413","https://openalex.org/W2994762488","https://openalex.org/W3006036681","https://openalex.org/W3146188354","https://openalex.org/W4229719928","https://openalex.org/W4242096891","https://openalex.org/W4249923483"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W1486544172","https://openalex.org/W4206324154","https://openalex.org/W1978931242","https://openalex.org/W2154629969"],"abstract_inverted_index":{"As":[0],"large-scale":[1,85],"systems":[2],"evolve":[3],"towards":[4],"post-petascale":[5],"computing,":[6],"it":[7],"is":[8,30,40,50,74],"crucial":[9],"to":[10,18,36,63,137,149,164],"focus":[11],"on":[12,22,103,111],"providing":[13],"fault-tolerance":[14],"strategies":[15],"that":[16,97,114,128,143],"aim":[17],"minimize":[19],"fault\u2019s":[20],"effects":[21],"applications.":[23],"By":[24],"far":[25],"the":[26,31,45,76],"most":[27],"popular":[28],"technique":[29],"checkpoint\u2013restart":[32],"strategy.":[33],"A":[34],"complement":[35],"this":[37,90],"classical":[38],"approach":[39,127],"failure":[41],"avoidance,":[42],"by":[43,75,84,144],"which":[44,175],"occurrence":[46],"of":[47,71,78,95,158,168],"a":[48,59,93,124,156,172],"fault":[49,181],"predicted":[51],"and":[52,66,120,161],"proactive":[53,180],"measures":[54],"are":[55],"taken.":[56],"This":[57],"requires":[58],"reliable":[60],"prediction":[61,73,154],"system":[62,79],"anticipate":[64],"failures":[65,116,170],"their":[67],"locations.":[68],"One":[69],"way":[70],"offering":[72],"analysis":[77,131],"logs":[80],"generated":[81],"during":[82],"production":[83,105],"systems.":[86,109],"Current":[87],"research":[88],"in":[89,135,171,179],"field":[91],"presents":[92],"number":[94],"limitations":[96],"make":[98],"them":[99],"unusable":[100],"for":[101],"running":[102],"real":[104],"high-performance":[106],"computing":[107],"(HPC)":[108],"Based":[110],"our":[112,153],"observations":[113],"different":[115,118],"have":[117],"distributions":[119],"behaviours,":[121],"we":[122],"propose":[123],"novel":[125],"hybrid":[126],"combines":[129],"signal":[130],"with":[132],"data":[133],"mining":[134],"order":[136],"overcome":[138],"current":[139],"limitations.":[140],"We":[141],"show":[142],"analysing":[145],"each":[146],"event":[147],"according":[148],"its":[150,162,177],"specific":[151],"behaviour,":[152],"provides":[155],"precision":[157],"over":[159],"90%":[160],"able":[163],"discover":[165],"about":[166],"50%":[167],"all":[169],"system,":[173],"result":[174],"allows":[176],"integration":[178],"tolerance":[182],"protocols.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
