{"id":"https://openalex.org/W2030011908","doi":"https://doi.org/10.1145/1989323.1989440","title":"A Hadoop based distributed loading approach to parallel data warehouses","display_name":"A Hadoop based distributed loading approach to parallel data warehouses","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2030011908","doi":"https://doi.org/10.1145/1989323.1989440","mag":"2030011908"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of 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/A5101854939","display_name":"Yu Xu","orcid":"https://orcid.org/0000-0003-1498-8331"},"institutions":[{"id":"https://openalex.org/I4210158714","display_name":"Teradata (United States)","ror":"https://ror.org/04vkkat38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158714"]},{"id":"https://openalex.org/I108650528","display_name":"Teradata (United Kingdom)","ror":"https://ror.org/00gze1672","country_code":"GB","type":"company","lineage":["https://openalex.org/I108650528","https://openalex.org/I4210158714"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Yu Xu","raw_affiliation_strings":["Teradata, San Diego, USA","Teradata, San Diego, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Teradata, San Diego, USA","institution_ids":["https://openalex.org/I4210158714"]},{"raw_affiliation_string":"Teradata, San Diego, USA#TAB#","institution_ids":["https://openalex.org/I108650528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049019411","display_name":"Pekka Kostamaa","orcid":"https://orcid.org/0000-0001-8224-6220"},"institutions":[{"id":"https://openalex.org/I4210158714","display_name":"Teradata (United States)","ror":"https://ror.org/04vkkat38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pekka Kostamaa","raw_affiliation_strings":["Teradata, El Segundo, USA"],"affiliations":[{"raw_affiliation_string":"Teradata, El Segundo, USA","institution_ids":["https://openalex.org/I4210158714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538922","display_name":"Yan Qi","orcid":"https://orcid.org/0000-0002-3168-4332"},"institutions":[{"id":"https://openalex.org/I4210158714","display_name":"Teradata (United States)","ror":"https://ror.org/04vkkat38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158714"]},{"id":"https://openalex.org/I108650528","display_name":"Teradata (United Kingdom)","ror":"https://ror.org/00gze1672","country_code":"GB","type":"company","lineage":["https://openalex.org/I108650528","https://openalex.org/I4210158714"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yan Qi","raw_affiliation_strings":["Teradata, San Diego, USA","Teradata, San Diego, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Teradata, San Diego, USA","institution_ids":["https://openalex.org/I4210158714"]},{"raw_affiliation_string":"Teradata, San Diego, USA#TAB#","institution_ids":["https://openalex.org/I108650528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102353226","display_name":"Jian Wen","orcid":"https://orcid.org/0000-0002-1759-4277"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wen","raw_affiliation_strings":["UC Riverside, Riverside, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006877684","display_name":"Kevin Zhao","orcid":"https://orcid.org/0000-0002-2444-4816"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Keliang Zhao","raw_affiliation_strings":["UC San Diego, San Diego, USA","UC San Diego, San Diego, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"UC San Diego, San Diego, USA","institution_ids":["https://openalex.org/I2800935791"]},{"raw_affiliation_string":"UC San Diego, San Diego, USA#TAB#","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101854939"],"corresponding_institution_ids":["https://openalex.org/I108650528","https://openalex.org/I4210158714"],"apc_list":null,"apc_paid":null,"fwci":3.6947,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93629495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1091","last_page":"1100"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9961000084877014,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9940000176429749,"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":0.8076534867286682},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7919260263442993},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.6147472858428955},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6026771664619446},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.591410756111145},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5492808222770691},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.47298821806907654},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4185999035835266},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.4102587103843689},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3189570903778076},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.09055665135383606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076534867286682},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7919260263442993},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.6147472858428955},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6026771664619446},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.591410756111145},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5492808222770691},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.47298821806907654},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4185999035835266},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.4102587103843689},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3189570903778076},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.09055665135383606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1967344300","https://openalex.org/W1977545325","https://openalex.org/W1993892970","https://openalex.org/W2035543557","https://openalex.org/W2049160854","https://openalex.org/W2086747090","https://openalex.org/W2122465391","https://openalex.org/W2142031898","https://openalex.org/W2752885492","https://openalex.org/W4372046852","https://openalex.org/W6992951189","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W3089119258","https://openalex.org/W2923327995","https://openalex.org/W3209916128","https://openalex.org/W2296277904","https://openalex.org/W2354643924","https://openalex.org/W4285172683","https://openalex.org/W2233862028","https://openalex.org/W1973138370"],"abstract_inverted_index":{"One":[0,57],"critical":[1],"part":[2],"of":[3,98,120,184,328,414],"building":[4],"and":[5,74,143,271,312,331,382,397,406],"running":[6,172],"a":[7,26,36,91,113,174,188,283,377,383],"data":[8,30,32,66,71,80,100,151,205,237,248,253,344,360,408],"warehouse":[9],"is":[10,24,68,149,238,243,258,285,302],"the":[11,19,61,96,104,199,215,229,236,247,252,256,289,303,317,351,357,412,415],"ETL":[12,21],"(Extraction":[13],"Transformation":[14],"Loading)":[15],"process.":[16],"In":[17,177],"fact,":[18],"growing":[20],"tool":[22],"market":[23],"already":[25],"multi-billion-dollar":[27],"market.":[28],"Getting":[29],"into":[31],"warehouses":[33,67,81],"has":[34],"been":[35],"hindering":[37],"factor":[38],"to":[39,65,130,192,203,206,209,231,240,250,260,269,274,298,340,346,356,371,388,392,410],"wider":[40],"potential":[41],"database":[42,55],"applications":[43],"such":[44],"as":[45,48,187,198,321],"scientific":[46],"computing,":[47,162],"discussed":[49],"in":[50,79,152,287,296,306,362],"recent":[51],"panels":[52],"at":[53],"various":[54],"conferences.":[56],"particular":[58],"problem":[59],"with":[60],"current":[62],"load":[63,86,117,190,201,342],"approaches":[64],"that":[69,137,150],"while":[70],"are":[72,123,155],"partitioned":[73,156],"replicated":[75],"across":[76,157],"all":[77,214],"nodes":[78,159],"powered":[82],"by":[83,133,325],"parallel":[84,161,165,297,348,394],"DBMS(PDBMS),":[85],"utilities":[87],"typically":[88],"reside":[89],"on":[90,112,173,316,350,404],"single":[92,114,175],"node":[93],"which":[94,163,301],"face":[95],"issues":[97,122],"i)":[99,223],"loss/data":[101],"availability":[102],"if":[103],"node/hard":[105],"drives":[106],"crash;":[107],"ii)":[108,234],"file":[109,230,257,284,290],"size":[110],"limit":[111],"node;":[115],"iii)":[116,263],"performance.":[118],"All":[119],"these":[121],"mostly":[124],"handled":[125],"manually":[126],"or":[127,276],"only":[128],"helped":[129],"some":[131],"degree":[132],"tools.":[134],"We":[135,195,212,375,401],"notice":[136],"one":[138],"common":[139],"thing":[140],"between":[141],"Hadoop":[142,186,197,311],"Teradata":[144,193,210,261,299,313,347,373,393],"Enterprise":[145],"Data":[146],"Warehouse":[147],"(EDW)":[148],"both":[153,310],"systems":[154],"multiple":[158],"for":[160,170,228,246],"creates":[164],"loading":[166],"opportunities":[167],"not":[168,244],"possible":[169],"DBMSs":[171],"node.":[176],"this":[178,307],"paper":[179],"we":[180,335,365],"describe":[181],"our":[182],"approach":[183],"using":[185],"distributed":[189,286],"strategy":[191],"EDW.":[194,211],"use":[196],"intermediate":[200],"server":[202],"store":[204],"be":[207,232,267,292],"loaded":[208,259,293],"gain":[213],"benefits":[216],"from":[217],"HDFS":[218,343,369,390],"(Hadoop":[219],"Distributed":[220],"File":[221],"System):":[222],"significantly":[224],"increased":[225],"disk":[226],"space":[227],"loaded;":[233],"once":[235],"written":[239],"HDFS,":[241,288,363],"it":[242],"necessary":[245],"sources":[249],"keep":[251],"even":[254],"before":[255],"EDW;":[262],"MapReduce":[264],"programs":[265],"can":[266,291,366],"used":[268],"transform":[270],"add":[272],"structures":[273],"unstructured":[275],"semi-structured":[277],"data;":[278],"iv)":[279],"more":[280,294],"importantly":[281],"since":[282],"quickly":[295],"EDW,":[300],"main":[304],"focus":[305],"paper.":[308],"When":[309],"EDW":[314],"coexist":[315],"same":[318,352],"hardware":[319,330],"platform,":[320],"being":[322],"increasingly":[323],"required":[324],"customers":[326],"because":[327],"reduced":[329],"system":[332],"administration":[333],"costs,":[334],"have":[336],"another":[337],"optimization":[338],"opportunity":[339],"directly":[341],"blocks":[345,370,391],"units":[349,395],"nodes.":[353,374],"However,":[354],"due":[355],"inherent":[358],"non-uniform":[359],"distribution":[361],"rarely":[364],"avoid":[367],"transferring":[368],"remote":[372],"designed":[376],"polynomial":[378,384],"time":[379,385],"optimal":[380],"algorithm":[381,387],"approximate":[386],"assign":[389],"evenly":[396],"minimize":[398],"network":[399],"traffic.":[400],"performed":[402],"experiments":[403],"synthetic":[405],"real":[407],"sets":[409],"compare":[411],"performances":[413],"algorithms.":[416]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}