{"id":"https://openalex.org/W2136797898","doi":"https://doi.org/10.1109/ipdps.2012.107","title":"Taming of the Shrew: Modeling the Normal and Faulty Behaviour of Large-scale HPC Systems","display_name":"Taming of the Shrew: Modeling the Normal and Faulty Behaviour of Large-scale HPC Systems","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2136797898","doi":"https://doi.org/10.1109/ipdps.2012.107","mag":"2136797898"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2012.107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2012.107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 26th International Parallel and Distributed Processing Symposium","raw_type":"proceedings-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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana Gainaru","raw_affiliation_strings":["Computer Science Department, NCSA, UIUC, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, NCSA, UIUC, Urbana, IL, USA","institution_ids":[]}]},{"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 sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["INRIA, France","UIUC, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"UIUC, Urbana, IL, USA","institution_ids":["https://openalex.org/I183874917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110595734","display_name":"William Kramer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Kramer","raw_affiliation_strings":["NCSA, UIUC, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCSA, UIUC, Urbana, IL, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3159,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.98237103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1168","last_page":"1179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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":0.9998999834060669,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.742290735244751},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6598541736602783},{"id":"https://openalex.org/keywords/normality","display_name":"Normality","score":0.5227915644645691},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4802401661872864},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.45474904775619507},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4369148313999176},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4328320622444153},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3507001996040344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26401153206825256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742290735244751},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6598541736602783},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.5227915644645691},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4802401661872864},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.45474904775619507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4369148313999176},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4328320622444153},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3507001996040344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26401153206825256},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2012.107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2012.107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 26th International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W191651381","https://openalex.org/W1543008956","https://openalex.org/W1558516248","https://openalex.org/W1965396655","https://openalex.org/W1981432246","https://openalex.org/W1984980195","https://openalex.org/W2018212274","https://openalex.org/W2032467893","https://openalex.org/W2040352153","https://openalex.org/W2053691501","https://openalex.org/W2107263349","https://openalex.org/W2107814012","https://openalex.org/W2114554028","https://openalex.org/W2121561691","https://openalex.org/W2128265178","https://openalex.org/W2144569590","https://openalex.org/W2152671254","https://openalex.org/W2155043308","https://openalex.org/W2158907675","https://openalex.org/W2159963962","https://openalex.org/W2160100693","https://openalex.org/W2167439722","https://openalex.org/W2169490875","https://openalex.org/W2949365856","https://openalex.org/W3150262005","https://openalex.org/W6682655504","https://openalex.org/W6683432465"],"related_works":["https://openalex.org/W4321650139","https://openalex.org/W1999239650","https://openalex.org/W2169275958","https://openalex.org/W2405714784","https://openalex.org/W2106922074","https://openalex.org/W4285364886","https://openalex.org/W2912770476","https://openalex.org/W3156178883","https://openalex.org/W3159585989","https://openalex.org/W2050567447"],"abstract_inverted_index":{"HPC":[0,71,181],"systems":[1,33,72],"are":[2,17],"complex":[3],"machines":[4],"that":[5,166,197,247],"generate":[6],"a":[7,21,96,122,137,164,180,190,221,242,259],"huge":[8],"volume":[9],"of":[10,31,67,98,115,118,140,147,170,175,205,213,263],"system":[11,41,61,149,182,207],"state":[12,177],"data":[13],"called":[14],"\"events\".":[15],"Events":[16],"generated":[18],"without":[19],"following":[20],"general":[22],"consistent":[23],"rule":[24],"and":[25,28,43,63,78,86,120,144,184,224,234],"different":[26,35],"hardware":[27],"software":[29],"components":[30],"such":[32],"have":[34],"failure":[36,191,239],"rates.":[37],"Distinguishing":[38],"between":[39],"normal":[40,143,173],"behaviour":[42,114,146],"faulty":[44,145],"situation":[45],"relies":[46],"on":[47,230],"event":[48,81,104,178,251],"analysis.":[49],"Being":[50],"able":[51],"to":[52,74,125,129,253],"detect":[53],"quickly":[54],"deviations":[55],"from":[56,241],"normality":[57],"is":[58,64,95,187],"essential":[59],"for":[60],"administration":[62],"the":[65,88,112,142,148,168,172,193,206,211,231,264],"foundation":[66],"fault":[68,215,226],"prediction.":[69],"As":[70],"continue":[73],"grow":[75],"in":[76,100],"size":[77],"complexity,":[79],"mining":[80,105],"flows":[82],"become":[83],"more":[84,260],"challenging":[85],"with":[87],"upcoming":[89],"10":[90],"Pet":[91],"flop":[92],"systems,":[93],"there":[94],"lot":[97],"interest":[99],"this":[101,133],"topic.":[102],"Current":[103],"approaches":[106],"do":[107],"not":[108],"take":[109],"into":[110],"consideration":[111],"specific":[113,255],"each":[116,176,250],"type":[117],"events":[119],"as":[121],"consequence,":[123],"fail":[124],"analyze":[126],"them":[127],"according":[128,252],"their":[130],"characteristics.":[131],"In":[132],"paper":[134],"we":[135,219,257],"propose":[136],"novel":[138],"way":[139],"characterizing":[141],"by":[150,248],"using":[151],"signal":[152],"analysis":[153,156],"concepts.":[154],"All":[155],"modules":[157],"create":[158],"ELSA":[159],"(Event":[160],"Log":[161],"Signal":[162],"Analyzer),":[163],"toolkit":[165],"has":[167],"purpose":[169],"modelling":[171],"flow":[174],"during":[179],"lifetime,":[183],"how":[185],"it":[186,236],"affected":[188],"when":[189],"hits":[192],"system.":[194,244,266],"We":[195,245],"show":[196,246],"these":[198],"extracted":[199,232],"models":[200],"provide":[201],"an":[202],"accurate":[203],"view":[204],"output,":[208],"which":[209],"improves":[210],"effectiveness":[212],"proactive":[214],"tolerance":[216],"algorithms.":[217],"Specifically,":[218],"implemented":[220],"filtering":[222],"algorithm":[223],"short-term":[225],"prediction":[227],"methodology":[228],"based":[229],"model":[233],"test":[235],"against":[237],"real":[238],"traces":[240],"large-scale":[243],"analyzing":[249],"its":[254],"behaviour,":[256],"get":[258],"realistic":[261],"overview":[262],"entire":[265]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}