{"id":"https://openalex.org/W2063509861","doi":"https://doi.org/10.1109/bigdata.2014.7004315","title":"Astro: A predictive model for anomaly detection and feedback-based scheduling on Hadoop","display_name":"Astro: A predictive model for anomaly detection and feedback-based scheduling on Hadoop","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2063509861","doi":"https://doi.org/10.1109/bigdata.2014.7004315","mag":"2063509861"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5000208211","display_name":"Chaitali Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitali Gupta","raw_affiliation_strings":["Ebay Inc., San Jose, California","eBay Inc. San Jose, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ebay Inc., San Jose, California","institution_ids":["https://openalex.org/I4210150719"]},{"raw_affiliation_string":"eBay Inc. San Jose, California","institution_ids":["https://openalex.org/I4210150719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029084887","display_name":"Mayank Bansal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Bansal","raw_affiliation_strings":["Ebay Inc., San Jose, California","eBay Inc. San Jose, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ebay Inc., San Jose, California","institution_ids":["https://openalex.org/I4210150719"]},{"raw_affiliation_string":"eBay Inc. San Jose, California","institution_ids":["https://openalex.org/I4210150719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073793159","display_name":"Tzu-Cheng Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tzu-Cheng Chuang","raw_affiliation_strings":["Ebay Inc., San Jose, California","eBay Inc. San Jose, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ebay Inc., San Jose, California","institution_ids":["https://openalex.org/I4210150719"]},{"raw_affiliation_string":"eBay Inc. San Jose, California","institution_ids":["https://openalex.org/I4210150719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101502254","display_name":"Ranjan Sinha","orcid":"https://orcid.org/0000-0003-2485-8549"},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjan Sinha","raw_affiliation_strings":["Ebay Inc., San Jose, California","eBay Inc. San Jose, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ebay Inc., San Jose, California","institution_ids":["https://openalex.org/I4210150719"]},{"raw_affiliation_string":"eBay Inc. San Jose, California","institution_ids":["https://openalex.org/I4210150719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090314378","display_name":"Sami Ben-Romdhane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sami Ben-romdhane","raw_affiliation_strings":["Ebay Inc., San Jose, California","eBay Inc. San Jose, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ebay Inc., San Jose, California","institution_ids":["https://openalex.org/I4210150719"]},{"raw_affiliation_string":"eBay Inc. San Jose, California","institution_ids":["https://openalex.org/I4210150719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6408,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88548001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"854","last_page":"862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9966999888420105,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9965999722480774,"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":0.8195551037788391},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.738793671131134},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6475595235824585},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.618386447429657},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5630168914794922},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5009970664978027},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4639555811882019},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.451539546251297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4506318271160126},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.42794668674468994},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.41911500692367554},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.35078856348991394},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2049914002418518},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08968839049339294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195551037788391},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.738793671131134},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6475595235824585},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.618386447429657},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5630168914794922},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5009970664978027},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4639555811882019},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.451539546251297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4506318271160126},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.42794668674468994},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.41911500692367554},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35078856348991394},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2049914002418518},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08968839049339294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W119120569","https://openalex.org/W1591888204","https://openalex.org/W1965626898","https://openalex.org/W1976821017","https://openalex.org/W1988301066","https://openalex.org/W2029324211","https://openalex.org/W2048295208","https://openalex.org/W2053691501","https://openalex.org/W2094924503","https://openalex.org/W2105947650","https://openalex.org/W2117020308","https://openalex.org/W2119381450","https://openalex.org/W2120694635","https://openalex.org/W2133524609","https://openalex.org/W2154983209","https://openalex.org/W2161234420","https://openalex.org/W2166858086","https://openalex.org/W2173213060","https://openalex.org/W6604840855","https://openalex.org/W6635271661","https://openalex.org/W6657652657","https://openalex.org/W6677690934","https://openalex.org/W6677844719","https://openalex.org/W6683682350"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2115292631"],"abstract_inverted_index":{"The":[0,131,166,191,237],"sheer":[1],"growth":[2],"in":[3,20,47,134,172,226],"data":[4],"volume":[5],"and":[6,17,26,80,98,124,152,175,198,210,232],"Hadoop":[7,52,129],"cluster":[8,23,53,76,102,143,174,216,247,275],"size":[9],"make":[10],"it":[11,206],"a":[12,21,28,44,50,94,114,121,139,178],"significant":[13],"challenge":[14],"to":[15,55,78,127,159,203,208,219,224,228,254],"diagnose":[16],"locate":[18],"problems":[19],"production-level":[22],"environment":[24],"efficiently":[25],"within":[27],"short":[29],"period":[30],"of":[31,42,100,120,142,163,181,201,234,246,260,270],"time.":[32],"Often":[33],"times,":[34],"the":[35,73,81,84,101,128,164,173,186,189,195,199,214,235,241,258,261,268,274],"distributed":[36],"monitoring":[37,150],"systems":[38],"are":[39,147],"not":[40],"capable":[41],"detecting":[43],"problem":[45,85,111],"well":[46],"advance":[48],"when":[49,75,83],"large-scale":[51],"starts":[54,77],"deteriorate":[56,79],"i":[57,67],"n":[58,68],"performance":[59],"or":[60,218],"becomes":[61],"unavailable.":[62],"Thus,":[63],"inc":[64],"o":[65],"m":[66],"g":[69],"workloads,":[70],"scheduled":[71],"between":[72],"time":[74,82,269],"is":[86],"identified,":[87],"suffer":[88],"from":[89,213],"longer":[90],"execution":[91],"times.":[92],"As":[93],"result,":[95],"both":[96,230],"reliability":[97,233],"throughput":[99,231],"reduce":[103,211],"significantly.":[104],"In":[105],"this":[106,110],"paper,":[107],"we":[108],"address":[109],"by":[112,149,251,265],"proposing":[113],"system":[115],"called":[116],"Astro,":[117],"which":[118],"consists":[119],"predictive":[122,132,168],"model":[123,133,153,169],"an":[125],"extension":[126],"scheduler.":[130],"Astro":[135,167,192,242],"takes":[136],"into":[137],"account":[138],"rich":[140],"set":[141,180],"behavioral":[144],"information":[145],"that":[146,183,240],"collected":[148],"processes":[151],"them":[154],"using":[155],"machine":[156],"learning":[157],"algorithms":[158],"predict":[160],"future":[161],"behavior":[162],"cluster.":[165,236],"detects":[170],"anomalies":[171],"also":[176],"identifies":[177],"ranked":[179],"metrics":[182,202],"have":[184],"contributed":[185],"most":[187],"towards":[188],"problem.":[190],"scheduler":[193,243],"uses":[194],"prediction":[196],"outcome":[197],"list":[200],"decide":[204],"whether":[205],"needs":[207],"move":[209],"workloads":[212],"problematic":[215],"nodes":[217],"prevent":[220],"additional":[221],"workload":[222],"allocations":[223],"them,":[225],"order":[227],"improve":[229],"results":[238],"demonstrate":[239],"improves":[244],"usage":[245],"compute":[248],"resources":[249],"significantly":[250],"64.23%":[252],"compared":[253],"traditional":[255],"Hadoop.":[256],"Furthermore,":[257],"runtime":[259],"benchmark":[262],"application":[263],"reduced":[264],"26.68%":[266],"during":[267],"anomaly,":[271],"thus":[272],"improving":[273],"throughput.":[276]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}