{"id":"https://openalex.org/W2947006004","doi":"https://doi.org/10.1186/s40537-019-0196-1","title":"Evaluating partitioning and bucketing strategies for Hive-based Big Data Warehousing systems","display_name":"Evaluating partitioning and bucketing strategies for Hive-based Big Data Warehousing systems","publication_year":2019,"publication_date":"2019-05-06","ids":{"openalex":"https://openalex.org/W2947006004","doi":"https://doi.org/10.1186/s40537-019-0196-1","mag":"2947006004"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-019-0196-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0196-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0196-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0196-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101770933","display_name":"Eduarda Costa","orcid":"https://orcid.org/0000-0003-3459-0195"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Eduarda Costa","raw_affiliation_strings":["ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670597","display_name":"Carlos Costa","orcid":"https://orcid.org/0000-0003-0011-6030"},"institutions":[{"id":"https://openalex.org/I4210090193","display_name":"Centro de Computa\u00e7\u00e3o Gr\u00e1fica","ror":"https://ror.org/00aahnw66","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210090193"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Carlos Costa","raw_affiliation_strings":["ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal","Center for Computer Graphics, University of Minho, 4800 058, Guimar\u00e3es, Portugal","Center for Computer Graphics, University of Minho, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"Center for Computer Graphics, University of Minho, 4800 058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4210090193","https://openalex.org/I99682543"]},{"raw_affiliation_string":"Center for Computer Graphics, University of Minho, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4210090193","https://openalex.org/I99682543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042295020","display_name":"Maribel Yasmina Santos","orcid":"https://orcid.org/0000-0002-3249-6229"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Maribel Yasmina Santos","raw_affiliation_strings":["ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-3249-6229","affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, 4800 058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"ALGORITMI Research Centre, University of Minho, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1990,"currency":"USD","value_usd":1990},"apc_paid":{"value":1990,"currency":"USD","value_usd":1990},"fwci":3.5873,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93163591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9976999759674072,"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/T11478","display_name":"Caching and Content Delivery","score":0.9912999868392944,"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":0.8631981611251831},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7343288660049438},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6459591388702393},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6448200941085815},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.633853018283844},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5468302965164185},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3222326636314392},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08651235699653625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631981611251831},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7343288660049438},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6459591388702393},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6448200941085815},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.633853018283844},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5468302965164185},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3222326636314392},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08651235699653625},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-019-0196-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0196-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0196-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:repositorium.sdum.uminho.pt:1822/66781","is_oa":true,"landing_page_url":"http://hdl.handle.net/1822/66781","pdf_url":"http://hdl.handle.net/1822/66781","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:doaj.org/article:58a632489d2f4bbda2f77d5455b9c384","is_oa":true,"landing_page_url":"https://doaj.org/article/58a632489d2f4bbda2f77d5455b9c384","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 6, Iss 1, Pp 1-38 (2019)","raw_type":"article"},{"id":"pmh:oai:repositorium.uminho.pt:1822/66781","is_oa":true,"landing_page_url":"https://hdl.handle.net/1822/66781","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s40537-019-0196-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0196-1","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0196-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1516346500","display_name":null,"funder_award_id":"01-0145","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G1578237752","display_name":null,"funder_award_id":"COMPETE","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G1763632427","display_name":null,"funder_award_id":"POCI-01-0145","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2951523799","display_name":null,"funder_award_id":"Funding Reference: POCI-01- 0247-FEDER-002814","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3838636553","display_name":null,"funder_award_id":"-01-0247-","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3840324753","display_name":null,"funder_award_id":"POCI-01-0145-FEDER-","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4176497637","display_name":null,"funder_award_id":"COMPETE 2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5224927334","display_name":null,"funder_award_id":"POCI-01-","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5270559075","display_name":null,"funder_award_id":"POCI-01-0145-FEDER-007043","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7406260186","display_name":null,"funder_award_id":"UID/CEC/00319/2013","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7574042020","display_name":null,"funder_award_id":"00319","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8559185249","display_name":null,"funder_award_id":"POCI-01-0247","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8862270368","display_name":null,"funder_award_id":"POCI-01-0145-FEDER","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947006004.pdf","grobid_xml":"https://content.openalex.org/works/W2947006004.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W37241258","https://openalex.org/W170528110","https://openalex.org/W1505837402","https://openalex.org/W1993892970","https://openalex.org/W2018821139","https://openalex.org/W2090609886","https://openalex.org/W2109574129","https://openalex.org/W2110086534","https://openalex.org/W2277810561","https://openalex.org/W2460071091","https://openalex.org/W2493064216","https://openalex.org/W2497841879","https://openalex.org/W2500920028","https://openalex.org/W2511992115","https://openalex.org/W2518094867","https://openalex.org/W2533679444","https://openalex.org/W2537031909","https://openalex.org/W2553745069","https://openalex.org/W2574090651","https://openalex.org/W2589424763","https://openalex.org/W2610391677","https://openalex.org/W2735158567","https://openalex.org/W2740463104","https://openalex.org/W2740937960","https://openalex.org/W2748690181","https://openalex.org/W2777169332","https://openalex.org/W2785930933","https://openalex.org/W2792743796","https://openalex.org/W2804558854","https://openalex.org/W2884305502","https://openalex.org/W4243982364"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W4390608645","https://openalex.org/W2004734601","https://openalex.org/W2287264064","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W4405901645"],"abstract_inverted_index":{"Hive":[0,72],"has":[1],"long":[2],"been":[3],"one":[4],"of":[5,28,44,48,58,63,89,106,118,131,150,158,163,177,193,209,216,224],"the":[6,42,46,61,74,87,104,116,128,137,141,148,151,156,159,167,191,214,221],"industry-leading":[7],"systems":[8,51],"for":[9,40,52,77],"Data":[10,14,54,80,121],"Warehousing":[11,81],"in":[12,94,109,147,161,172,180,200,213],"Big":[13,53,79,120],"contexts,":[15],"mainly":[16],"organizing":[17],"data":[18,64,90,99],"into":[19],"databases,":[20],"tables,":[21],"partitions":[22,138],"and":[23,92,102,127],"buckets,":[24],"stored":[25],"on":[26,67,124],"top":[27],"an":[29],"unstructured":[30],"distributed":[31],"file":[32],"system":[33,160],"like":[34],"HDFS.":[35],"Some":[36],"studies":[37],"were":[38,183],"conducted":[39],"understanding":[41],"ways":[43],"optimizing":[45],"performance":[47],"several":[49],"storage":[50,75],"Warehousing.":[55],"However,":[56],"few":[57],"them":[59],"explore":[60],"impact":[62,88],"organization":[65,100],"strategies":[66,101,108],"query":[68,110],"performance,":[69],"when":[70],"using":[71,132],"as":[73],"technology":[76],"implementing":[78,119],"systems.":[82],"Therefore,":[83],"this":[84,173,210],"paper":[85],"evaluates":[86],"partitioning":[91,134],"bucketing":[93,194,217],"Hive-based":[95],"systems,":[96],"testing":[97],"different":[98],"verifying":[103],"efficiency":[105,157],"those":[107],"performance.":[111],"The":[112,185],"obtained":[113],"results":[114],"demonstrate":[115],"advantages":[117],"Warehouses":[122],"based":[123],"denormalized":[125],"models":[126],"potential":[129,198],"benefit":[130],"adequate":[133],"strategies.":[135],"Defining":[136],"aligned":[139],"with":[140,190],"attributes":[142],"that":[143],"are":[144],"frequently":[145],"used":[146],"conditions/filters":[149],"queries":[152],"can":[153],"significantly":[154],"increase":[155],"terms":[162],"response":[164],"time.":[165],"In":[166],"more":[168,206],"intensive":[169],"workload":[170],"benchmarked":[171],"paper,":[174],"overall":[175],"decreases":[176],"about":[178],"40%":[179],"processing":[181],"time":[182],"verified.":[184],"same":[186],"is":[187],"not":[188],"verified":[189],"use":[192,208],"strategies,":[195],"which":[196],"shows":[197],"benefits":[199],"very":[201],"specific":[202],"scenarios,":[203],"suggesting":[204],"a":[205],"restricted":[207],"functionality,":[211],"namely":[212],"context":[215],"two":[218],"tables":[219],"by":[220],"join":[222],"attribute":[223],"these":[225],"tables.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}
