{"id":"https://openalex.org/W3174833296","doi":"https://doi.org/10.1109/tr.2021.3085582","title":"Data-Driven Application-Oriented Reliability Model of a High-Performance Computing System","display_name":"Data-Driven Application-Oriented Reliability Model of a High-Performance Computing System","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3174833296","doi":"https://doi.org/10.1109/tr.2021.3085582","mag":"3174833296"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2021.3085582","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5060720579","display_name":"Bentolhoda Jafary","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]},{"id":"https://openalex.org/I60617922","display_name":"AeroVironment (United States)","ror":"https://ror.org/05cfcmn93","country_code":"US","type":"company","lineage":["https://openalex.org/I60617922"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bentolhoda Jafary","raw_affiliation_strings":["AeroVironment, Inc., Simi Valley, CA, USA","Department of Electrical and Computer Engineering, University of Massachusetts Dartmouth, Dartmouth, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts Dartmouth, Dartmouth, MA, USA","institution_ids":["https://openalex.org/I100633361"]},{"raw_affiliation_string":"AeroVironment, Inc., Simi Valley, CA, USA","institution_ids":["https://openalex.org/I60617922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016778130","display_name":"Saurabh Jha","orcid":"https://orcid.org/0000-0003-0926-0776"},"institutions":[{"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":"Saurabh Jha","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032820782","display_name":"Lance Fiondella","orcid":"https://orcid.org/0000-0002-4572-6599"},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lance Fiondella","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Massachusetts Dartmouth, Dartmouth, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts Dartmouth, Dartmouth, MA, USA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067802693","display_name":"Ravishankar K. Iyer","orcid":"https://orcid.org/0000-0003-2245-3038"},"institutions":[{"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":"Ravishankar K. Iyer","raw_affiliation_strings":["Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.542,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.786866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":76,"max":79},"biblio":{"volume":"71","issue":"2","first_page":"603","last_page":"615"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9989,"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":0.9986,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.7931238}],"concepts":[{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.7931238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669676},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.73206407},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.66703665},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5705253},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5206546},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5073773},{"id":"https://openalex.org/C167343916","wikidata":"https://www.wikidata.org/wiki/Q6888384","display_name":"Modeling and simulation","level":2,"score":0.42109913},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22155493},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.18293685},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13494623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13362873},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2021.3085582","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524313320","https://openalex.org/W1553890549","https://openalex.org/W191492107","https://openalex.org/W1999900893","https://openalex.org/W2001495258","https://openalex.org/W2025024269","https://openalex.org/W2027716782","https://openalex.org/W2033656974","https://openalex.org/W2045879521","https://openalex.org/W2049459394","https://openalex.org/W2072637364","https://openalex.org/W2074787299","https://openalex.org/W2081612620","https://openalex.org/W2093736609","https://openalex.org/W2105524676","https://openalex.org/W2121404908","https://openalex.org/W2123475473","https://openalex.org/W2129935547","https://openalex.org/W2142812297","https://openalex.org/W2145071552","https://openalex.org/W2155204206","https://openalex.org/W2156205360","https://openalex.org/W2161537327","https://openalex.org/W2161833190","https://openalex.org/W2411972182","https://openalex.org/W2595507424","https://openalex.org/W2743531752","https://openalex.org/W4237492115","https://openalex.org/W4256158364","https://openalex.org/W4297690074","https://openalex.org/W4298200086"],"related_works":["https://openalex.org/W4251454458","https://openalex.org/W4214827973","https://openalex.org/W2954002293","https://openalex.org/W2892741875","https://openalex.org/W2164372000","https://openalex.org/W2161582432","https://openalex.org/W2109143577","https://openalex.org/W2080951167","https://openalex.org/W2078264086","https://openalex.org/W2046276983"],"abstract_inverted_index":{"Reliability":[0],"analysis":[1,119,152],"and":[2,23,36,49,72,91,187,195],"performance":[3],"evaluation":[4],"are":[5],"complementary":[6],"methods":[7],"to":[8,47,69,105,110,182,191],"quantify":[9],"nonfunctional":[10],"aspects":[11],"of":[12,18,38,57,82,89,100,118,127,136,145,153,163],"a":[13,16,54,93,125],"system.":[14],"However,":[15],"range":[17],"factors":[19],"such":[20],"as":[21],"concurrency":[22],"heterogeneity":[24],"quickly":[25],"exacerbate":[26],"the":[27,80,87,98,106,116,122,137,143,154,160,176],"state-space":[28],"explosion":[29],"problem":[30],"when":[31],"attempting":[32],"detailed":[33],"system-level":[34],"modeling":[35,48,76,177],"simulation":[37],"high-performance":[39],"computing":[40],"(HPC)":[41],"systems.":[42],"To":[43],"overcome":[44],"these":[45],"impediments":[46],"analysis,":[50],"this":[51],"article":[52],"develops":[53],"hierarchical":[55],"model":[56,123,155],"an":[58,65],"application":[59,112,170],"that":[60,79,158],"implements":[61],"checkpointing":[62],"running":[63],"in":[64,86],"HPC":[66],"environment":[67],"subject":[68],"application,":[70],"network,":[71],"system-wide":[73],"outages.":[74],"The":[75],"approach":[77,178],"ensures":[78],"number":[81,88,99],"states":[83,102],"is":[84],"linear":[85],"checkpoints":[90],"possesses":[92],"low":[94],"constant":[95],"factor":[96],"for":[97],"recovery":[101],"most":[103,167],"relevant":[104],"external":[107],"influences":[108],"contributing":[109],"degraded":[111],"performance.":[113],"We":[114,172],"illustrate":[115],"types":[117],"enabled":[120],"by":[121],"through":[124],"series":[126],"examples":[128],"with":[129],"parameters":[130,156],"determined":[131],"empirically":[132],"from":[133],"data":[134],"logs":[135],"Blue":[138],"Waters":[139],"supercomputer":[140],"located":[141],"at":[142,147],"University":[144],"Illinois":[146],"Urbana\u2013Champaign.":[148],"A":[149],"comprehensive":[150],"comparative":[151],"indicates":[157],"lowering":[159],"failure":[161],"rate":[162],"network":[164],"nodes":[165],"would":[166],"significantly":[168],"reduce":[169],"downtime.":[171],"also":[173],"discuss":[174],"how":[175],"can":[179],"be":[180],"used":[181],"objectively":[183],"assess":[184],"both":[185],"current":[186],"hypothetical":[188],"future":[189],"systems":[190],"identify":[192],"competitive":[193],"designs":[194],"enhancements.":[196]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3174833296","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2024-12-11T19:17:16.758793","created_date":"2021-07-05"}