{"id":"https://openalex.org/W2170997892","doi":"https://doi.org/10.1145/2783258.2788600","title":"ALOJA-ML","display_name":"ALOJA-ML","publication_year":2015,"publication_date":"2015-08-07","ids":{"openalex":"https://openalex.org/W2170997892","doi":"https://doi.org/10.1145/2783258.2788600","mag":"2170997892"},"language":"en","primary_location":{"id":"doi:10.1145/2783258.2788600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2788600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1511.02030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Josep Llu\u00eds Berral","orcid":null},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Josep Llu\u00eds Berral","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nicolas Poggi","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nicolas Poggi","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"David Carrera","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Carrera","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), BarcelonaTech (UPC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aaron Call","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aaron Call","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rob Reinauer","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Reinauer","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Daron Green","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daron Green","raw_affiliation_strings":["Microsoft Research, Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":4.2047,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94590579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1701","last_page":"1710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9986000061035156,"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":0.9986000061035156,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7864000201225281},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7314000129699707},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5572999715805054},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.5507000088691711},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5200999975204468},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4975000023841858},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4699000120162964},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4560999870300293}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7864000201225281},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7314000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246000170707703},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C178059732","wikidata":"https://www.wikidata.org/wiki/Q1982529","display_name":"Software performance testing","level":5,"score":0.266400009393692},{"id":"https://openalex.org/C135510737","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance indicator","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2783258.2788600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2788600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1511.02030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1511.02030","pdf_url":"https://arxiv.org/pdf/1511.02030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:upcommons.upc.edu:2117/77791","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/77791","pdf_url":"https://upcommons.upc.edu/bitstreams/28d244f1-370d-4473-80e3-3453ceca75bb/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1511.02030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1511.02030","pdf_url":"https://arxiv.org/pdf/1511.02030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1325278347","display_name":null,"funder_award_id":"639595","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5399556803","display_name":null,"funder_award_id":"This project has received funding from the Europea","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5495974744","display_name":null,"funder_award_id":"TIN2012-34557 and 2014SGR1051","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G7191662350","display_name":"Holistic Integration of Emerging Supercomputing Technologies","funder_award_id":"639595","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1572978214","https://openalex.org/W1834532152","https://openalex.org/W2049624433","https://openalex.org/W2112731002","https://openalex.org/W2133990480","https://openalex.org/W2141249441","https://openalex.org/W2147169507","https://openalex.org/W2155072926","https://openalex.org/W2165844343","https://openalex.org/W2189125735"],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2,67],"ALOJA-Machine":[3],"Learning":[4],"(ALOJA-ML)":[5],"an":[6,97,167],"extension":[7],"to":[8,17,53,116,153,195,221,249,271,293],"the":[9,29,33,42,55,93,120,123,207,231,251,257,274,280,295],"ALOJA":[10,94,136,287],"project":[11,40,95],"that":[12,143],"uses":[13],"machine":[14],"learning":[15,272],"techniques":[16],"interpret":[18],"Hadoop":[19,66,104,175],"benchmark":[20,240],"performance":[21,24,75,190],"data":[22,258],"and":[23,35,51,74,85,114,118,129,160,213,216,260,264,290,297],"tuning;":[25],"here":[26],"we":[27],"detail":[28],"approach,":[30],"efficacy":[31],"of":[32,45,57,81,122,150,158,184,199,206,299],"model":[34],"initial":[36],"results.":[37],"The":[38,187],"ALOJA-ML":[39,164],"is":[41],"latest":[43],"phase":[44],"a":[46,68,78,111,144,155,181,219],"long-term":[47],"collaboration":[48],"between":[49],"BSC":[50],"Microsoft,":[52],"automate":[54],"characterization":[56],"cost-effectiveness":[58,121],"on":[59,64,77,86,254],"Big":[60,300],"Data":[61,301],"deployments,":[62],"focusing":[63],"Hadoop.":[65],"complex":[69],"execution":[70,197,208],"environment,":[71],"where":[72],"costs":[73],"depends":[76],"large":[79,159],"number":[80],"software":[82],"(SW)":[83],"configurations":[84,212],"multiple":[87],"hardware":[88,125],"(HW)":[89],"deployment":[90,298],"choices.":[91],"Recently":[92],"presented":[96,276],"open,":[98],"vendor-neutral":[99],"repository,":[100],"featuring":[101],"over":[102],"16.000":[103],"executions.":[105],"These":[106],"results":[107],"are":[108],"accompanied":[109],"by":[110,173,235],"test":[112],"bed":[113],"tools":[115],"deploy":[117],"evaluate":[119],"different":[124],"configurations,":[126],"parameter":[127],"tunings,":[128],"Cloud":[130],"services.":[131],"Despite":[132],"early":[133],"success":[134],"within":[135],"from":[137,177,243,273,286],"expert-guided":[138],"benchmarking,":[139],"it":[140],"became":[141],"clear":[142],"genuinely":[145],"comprehensive":[146],"study":[147],"requires":[148],"automation":[149],"modeling":[151,174],"procedures":[152],"allow":[154,203],"systematic":[156],"analysis":[157],"resource-constrained":[161],"search":[162],"spaces.":[163],"provides":[165],"such":[166],"automated":[168],"system":[169],"allowing":[170],"knowledge":[171,261],"discovery":[172,262],"executions":[176],"observed":[178],"benchmarks":[179],"across":[180],"broad":[182],"set":[183],"configuration":[185],"parameters.":[186],"resulting":[188],"empirically-derived":[189],"models":[191,228,245],"can":[192,229,246,282],"be":[193,247],"used":[194,248],"forecast":[196],"behavior":[198],"various":[200],"workloads;":[201],"they":[202,217],"a-priori":[204],"prediction":[205],"times":[209],"for":[210],"new":[211],"HW":[214],"choices":[215],"offer":[218],"route":[220],"model-based":[222],"anomaly":[223],"detection.":[224],"In":[225,269],"addition,":[226],"these":[227],"guide":[230],"benchmarking":[232],"exploration":[233],"efficiently,":[234],"automatically":[236],"prioritizing":[237],"candidate":[238],"future":[239],"tests.":[241],"Insights":[242],"ALOJA-ML's":[244],"reduce":[250,266],"operational":[252],"time":[253],"clusters,":[255],"speed-up":[256],"acquisition":[259],"process,":[263],"importantly,":[265],"running":[267],"costs.":[268],"addition":[270],"methodology":[275],"in":[277,284],"this":[278],"work,":[279],"community":[281],"benefit":[283],"general":[285],"data-sets,":[288],"framework,":[289],"derived":[291],"insights":[292],"improve":[294],"design":[296],"applications.":[302]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2016-06-24T00:00:00"}
