{"id":"https://openalex.org/W4319165080","doi":"https://doi.org/10.1109/bigdata55660.2022.10020295","title":"Ruya: Memory-Aware Iterative Optimization of Cluster Configurations for Big Data Processing","display_name":"Ruya: Memory-Aware Iterative Optimization of Cluster Configurations for Big Data Processing","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4319165080","doi":"https://doi.org/10.1109/bigdata55660.2022.10020295"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020295","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020295","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/285012/2/285012.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017414190","display_name":"Jonathan F. Will","orcid":null},"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 Will","raw_affiliation_strings":["Technische Universität,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084056435","display_name":"Lauritz Thamsen","orcid":"https://orcid.org/0000-0003-3755-1503"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lauritz Thamsen","raw_affiliation_strings":["University of Glasgow,United Kingdom","University of Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"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 Universität,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024675213","display_name":"Dominik Scheinert","orcid":"https://orcid.org/0000-0003-0763-3233"},"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":"Dominik Scheinert","raw_affiliation_strings":["Technische Universität,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042349846","display_name":"Odej Kao","orcid":"https://orcid.org/0000-0001-6454-6799"},"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":"Odej Kao","raw_affiliation_strings":["Technische Universität,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8732,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77315609,"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":"161","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9937999844551086,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9810000061988831,"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":0.7956838607788086},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5203306674957275},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4903121292591095},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4775727093219757},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4771694242954254},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46912288665771484},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4627997577190399},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4528173506259918},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33828991651535034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24668538570404053},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1452418863773346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956838607788086},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5203306674957275},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4903121292591095},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4775727093219757},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4771694242954254},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46912288665771484},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4627997577190399},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4528173506259918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33828991651535034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24668538570404053},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1452418863773346},{"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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020295","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020295","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:285012","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":"https://eprints.gla.ac.uk/285012/2/285012.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:285012","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/66347.html>","pdf_url":"https://eprints.gla.ac.uk/285012/2/285012.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5899999737739563,"display_name":"Decent work and economic growth"}],"awards":[{"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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319165080.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2019751555","https://openalex.org/W2070600700","https://openalex.org/W2101234009","https://openalex.org/W2114896543","https://openalex.org/W2160121678","https://openalex.org/W2173213060","https://openalex.org/W2521550930","https://openalex.org/W2546571074","https://openalex.org/W2566979091","https://openalex.org/W2572526791","https://openalex.org/W2963642335","https://openalex.org/W2963822306","https://openalex.org/W2968631515","https://openalex.org/W3029946860","https://openalex.org/W3102428287","https://openalex.org/W3126778967","https://openalex.org/W3137810510","https://openalex.org/W3138614542","https://openalex.org/W3207844152","https://openalex.org/W3211837897","https://openalex.org/W3215201015","https://openalex.org/W3216845212","https://openalex.org/W4250180141","https://openalex.org/W4281490613","https://openalex.org/W4281890777","https://openalex.org/W4284879405","https://openalex.org/W4304820096","https://openalex.org/W4312780108","https://openalex.org/W6687322159","https://openalex.org/W6697698479","https://openalex.org/W6727576777","https://openalex.org/W6731596640","https://openalex.org/W6735916004"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4240326769"],"abstract_inverted_index":{"Selecting":[0],"appropriate":[1],"computational":[2],"resources":[3],"for":[4,14,58,72,133,157],"data":[5,18,76],"processing":[6,77],"jobs":[7],"on":[8,81,100,148,164],"large":[9],"clusters":[10],"is":[11,41,152],"difficult,":[12],"even":[13],"expert":[15],"users":[16],"like":[17],"engineers.":[19],"Inadequate":[20],"choices":[21],"can":[22,63],"result":[23],"in":[24,53],"vastly":[25],"increased":[26],"costs,":[27],"without":[28],"significantly":[29],"improving":[30],"performance.":[31],"One":[32],"crucial":[33],"aspect":[34],"of":[35,50,75,97,121,177],"selecting":[36],"an":[37,59,182],"efficient":[38],"resource":[39,61],"configuration":[40,62,137,150,184],"avoiding":[42],"memory":[43,49,109,123],"bottlenecks.":[44],"By":[45],"knowing":[46],"the":[47,55,98,107,134,158,190],"required":[48],"a":[51,70,84,102,118,149,165,175],"job":[52,91],"advance,":[54],"search":[56,86,128,132,142,178],"space":[57],"optimal":[60,156,183],"be":[64,155],"greatly":[65],"reduced.Therefore,":[66],"we":[67,89,113,130,173],"present":[68],"Ruya,":[69],"method":[71],"memory-aware":[73],"optimization":[74],"cluster":[78,115,136],"configurations":[79,116],"based":[80],"iteratively":[82,131],"exploring":[83],"narrowed-down":[85],"space.":[87],"First,":[88],"perform":[90],"profiling":[92],"runs":[93],"with":[94,117,138,167],"small":[95],"samples":[96],"dataset":[99,166],"just":[101],"single":[103],"machine":[104],"to":[105,154,180,189],"model":[106],"job\u2019s":[108],"usage":[110],"patterns.":[111],"Second,":[112],"prioritize":[114],"suitable":[119],"amount":[120],"total":[122],"and":[124,170],"within":[125],"this":[126],"reduced":[127],"space,":[129],"best":[135],"Bayesian":[139],"optimization.":[140],"This":[141],"process":[143],"stops":[144],"once":[145],"it":[146],"converges":[147],"that":[151],"believed":[153],"given":[159],"job.":[160],"In":[161],"our":[162],"evaluation":[163],"1031":[168],"Spark":[169],"Hadoop":[171],"jobs,":[172],"see":[174],"reduction":[176],"iterations":[179],"find":[181],"by":[185],"around":[186],"half,":[187],"compared":[188],"baseline.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2023-02-04T00:00:00"}