{"id":"https://openalex.org/W2289758322","doi":"https://doi.org/10.1109/iwqos.2015.7404739","title":"Catching failures of failures at big-data clusters: A two-level neural network approach","display_name":"Catching failures of failures at big-data clusters: A two-level neural network approach","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2289758322","doi":"https://doi.org/10.1109/iwqos.2015.7404739","mag":"2289758322"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos.2015.7404739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos.2015.7404739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 23rd International Symposium on Quality of Service (IWQoS)","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/A5088744660","display_name":"Andrea Ros\u00e0","orcid":"https://orcid.org/0000-0002-6467-0113"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Rosa","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e0 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013859152","display_name":"Lydia Y. Chen","orcid":"https://orcid.org/0000-0002-4228-6735"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lydia Y. Chen","raw_affiliation_strings":["Cloud Server Technologies Group, IBM Research Lab Zurich, R\u00fcschlikon, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Server Technologies Group, IBM Research Lab Zurich, R\u00fcschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074152163","display_name":"Walter Binder","orcid":"https://orcid.org/0000-0002-2477-2182"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Walter Binder","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e0 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4481,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82811508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9972000122070312,"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":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.8315388560295105},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7811358571052551},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6702567934989929},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5954180955886841},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48100170493125916},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.471329003572464},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4573987126350403},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3577570617198944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35275620222091675},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3506847620010376},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26786670088768005},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.091785728931427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315388560295105},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7811358571052551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6702567934989929},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5954180955886841},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48100170493125916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.471329003572464},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4573987126350403},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3577570617198944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35275620222091675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506847620010376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26786670088768005},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.091785728931427},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos.2015.7404739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos.2015.7404739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 23rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W104725487","https://openalex.org/W1510496002","https://openalex.org/W1555569599","https://openalex.org/W1601664780","https://openalex.org/W2006778428","https://openalex.org/W2007286423","https://openalex.org/W2025024269","https://openalex.org/W2031513172","https://openalex.org/W2042594277","https://openalex.org/W2118676041","https://openalex.org/W2129542763","https://openalex.org/W2161234420","https://openalex.org/W2215315572","https://openalex.org/W6604303105","https://openalex.org/W6630529663","https://openalex.org/W6683682350"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2499527417"],"abstract_inverted_index":{"Big-data":[0],"applications":[1],"are":[2,192],"becoming":[3],"the":[4,20,111,136],"core":[5],"of":[6,28,40,42,49,58,74,85,143,146,165,198,217],"today's":[7],"business":[8],"operations,":[9],"featuring":[10],"complex":[11,112],"data":[12],"structures":[13],"and":[14,53,90,116,118,127,139,178,209,220],"high":[15,225],"task":[16,179],"fan-out.":[17],"According":[18],"to":[19,69,82,194,207],"publicly":[21],"available":[22],"Google":[23,188],"trace,":[24,190],"more":[25],"than":[26],"40%":[27],"big-data":[29,64,201],"jobs":[30,45,167],"do":[31],"not":[32],"reach":[33],"successful":[34],"completion.":[35],"Interestingly,":[36],"a":[37,55,77,151,169,187],"significant":[38,215],"portion":[39],"tasks":[41,73,89,93,115,145,164,206],"such":[43,71],"failed":[44,51,72,75,144,147,163,166],"undergo":[46],"multiple":[47,83],"types":[48,84],"repetitive":[50],"executions":[52],"consume":[54],"non-negligible":[56],"amount":[57],"resources.":[59],"To":[60],"conserve":[61],"resources":[62],"for":[63],"clusters,":[65,202],"it":[66],"is":[67,173],"imperative":[68],"capture":[70,196],"jobs,":[76,117,148],"very":[78],"challenging":[79],"problem":[80],"due":[81],"failures":[86,197,199],"associated":[87],"with":[88],"highly":[91],"uneven":[92],"distribution.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98,156,191],"develop":[99,157],"an":[100,124],"on-line":[101],"two-level":[102],"Neural":[103],"Network":[104],"(NN)":[105],"model":[106,133],"which":[107],"can":[108],"accurately":[109,195],"untangle":[110],"dependencies":[113],"among":[114],"predict":[119],"their":[120],"execution":[121,180],"classes":[122,142],"in":[123],"extremely":[125],"dynamic":[126],"heterogeneous":[128],"system.":[129],"Our":[130],"proposed":[131],"NN":[132],"predicts":[134],"first":[135],"job":[137],"class,":[138],"secondly":[140],"three":[141],"based":[149],"on":[150,186],"sliding":[152],"learning":[153],"window.":[154],"Furthermore,":[155],"resource":[158],"conservation":[159],"policies":[160],"that":[161,172],"terminate":[162],"after":[168],"grace":[170],"period":[171],"derived":[174],"from":[175],"prediction":[176],"confidences":[177],"times.":[181],"Overall,":[182],"evaluating":[183],"our":[184],"results":[185],"cluster":[189],"able":[193],"at":[200],"mitigate":[203],"false":[204],"negative":[205],"1%,":[208],"efficiently":[210],"save":[211],"system":[212],"resources,":[213],"achieving":[214],"reductions":[216],"CPU,":[218],"memory":[219],"disk":[221],"consumption":[222],"-":[223],"as":[224,226],"49%.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"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":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}