{"id":"https://openalex.org/W3102428287","doi":"https://doi.org/10.1109/bigdata50022.2020.9377994","title":"Towards Collaborative Optimization of Cluster Configurations for Distributed Dataflow Jobs","display_name":"Towards Collaborative Optimization of Cluster Configurations for Distributed Dataflow Jobs","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3102428287","doi":"https://doi.org/10.1109/bigdata50022.2020.9377994","mag":"3102428287"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/66347.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002540373","display_name":"Jonathan Will","orcid":"https://orcid.org/0009-0005-7834-8845"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonathan Will","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051029385","display_name":"Jonathan Bader","orcid":"https://orcid.org/0000-0003-0391-728X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Bader","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084056435","display_name":"Lauritz Thamsen","orcid":"https://orcid.org/0000-0003-3755-1503"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lauritz Thamsen","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002540373"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":3.3383,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93736344,"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":"2851","last_page":"2856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9957000017166138,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.9717808961868286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8854519128799438},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7150813341140747},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5676653385162354},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5489318370819092},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5157192349433899},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4648206830024719},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.43631288409233093},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.4268789291381836},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.41899242997169495},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4148768484592438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37515726685523987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15854105353355408},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13150212168693542},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10713347792625427}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9717808961868286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8854519128799438},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7150813341140747},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5676653385162354},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5489318370819092},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5157192349433899},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4648206830024719},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.43631288409233093},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.4268789291381836},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.41899242997169495},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4148768484592438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37515726685523987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15854105353355408},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13150212168693542},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10713347792625427},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:268152","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2011.07965","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07965","pdf_url":"https://arxiv.org/pdf/2011.07965","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"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:268152","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5199999809265137,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3031800739","display_name":null,"funder_award_id":"BIFOLD","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7624340995","display_name":null,"funder_award_id":"01IS18025A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1529083614","https://openalex.org/W1535431348","https://openalex.org/W2002472616","https://openalex.org/W2114896543","https://openalex.org/W2130204178","https://openalex.org/W2189465200","https://openalex.org/W2309679942","https://openalex.org/W2521550930","https://openalex.org/W2528415359","https://openalex.org/W2566979091","https://openalex.org/W2572526791","https://openalex.org/W2604856537","https://openalex.org/W2776268681","https://openalex.org/W2793313422","https://openalex.org/W2794463473","https://openalex.org/W2906952167","https://openalex.org/W2946894050","https://openalex.org/W2963642335","https://openalex.org/W2963822306","https://openalex.org/W3009370840","https://openalex.org/W6631530656","https://openalex.org/W6632229964","https://openalex.org/W6679182178","https://openalex.org/W6687322159","https://openalex.org/W6697698479","https://openalex.org/W6727576777","https://openalex.org/W6735916004","https://openalex.org/W6749468489"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W4377693460","https://openalex.org/W2783505431","https://openalex.org/W2521947294","https://openalex.org/W4236419692","https://openalex.org/W2017802743"],"abstract_inverted_index":{"Analyzing":[0],"large":[1,17],"datasets":[2],"with":[3],"distributed":[4,52,93],"dataflow":[5,53,94],"systems":[6],"requires":[7,134],"the":[8,32,45,110,135],"use":[9,111],"of":[10,21,92,105,112],"clusters.":[11,29],"Public":[12],"cloud":[13],"providers":[14],"offer":[15],"a":[16,51,75],"variety":[18],"and":[19,38,57,67,86,130],"quantity":[20],"resources":[22,34],"that":[23,124],"can":[24,40,99],"be":[25,42,100],"used":[26],"for":[27,78],"such":[28],"However,":[30,116],"picking":[31],"appropriate":[33],"in":[35,131],"both":[36],"type":[37],"number":[39],"often":[41],"challenging,":[43],"as":[44],"selected":[46],"configuration":[47,63],"needs":[48],"to":[49,102,137],"match":[50],"job's":[54],"resource":[55,69],"demands":[56],"access":[58],"patterns.":[59],"A":[60],"good":[61],"cluster":[62,81],"avoids":[64],"hardware":[65],"bottlenecks":[66],"maximizes":[68],"utilization,":[70],"avoiding":[71],"costly":[72],"overprovisioning.We":[73],"propose":[74],"collaborative":[76],"approach":[77],"finding":[79],"optimal":[80],"configurations":[82],"based":[83],"on":[84,120],"sharing":[85],"learning":[87],"from":[88],"historical":[89,121],"runtime":[90,122],"data":[91,98,123],"jobs.":[95],"Collaboratively":[96],"shared":[97],"utilized":[101],"predict":[103],"runtimes":[104],"future":[106],"job":[107],"executions":[108],"through":[109],"specialized":[113],"regression":[114],"models.":[115],"training":[117],"prediction":[118],"models":[119,136],"were":[125],"produced":[126],"by":[127],"different":[128],"users":[129],"diverse":[132],"contexts":[133,140],"take":[138],"these":[139],"into":[141],"account.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-11-23T00:00:00"}
