{"id":"https://openalex.org/W2022678827","doi":"https://doi.org/10.1145/2628194.2628249","title":"CloudETL","display_name":"CloudETL","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2022678827","doi":"https://doi.org/10.1145/2628194.2628249","mag":"2022678827"},"language":"en","primary_location":{"id":"doi:10.1145/2628194.2628249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628194.2628249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Database Engineering &amp; Applications Symposium on - IDEAS '14","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100735899","display_name":"Xiufeng Liu","orcid":"https://orcid.org/0000-0001-5133-6688"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiufeng Liu","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010748912","display_name":"Christian Thomsen","orcid":"https://orcid.org/0000-0002-0862-0509"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian Thomsen","raw_affiliation_strings":["Aalborg University","[Aalborg university]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Aalborg university]","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061064237","display_name":"Torben Bach Pedersen","orcid":"https://orcid.org/0000-0002-1615-777X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Torben Bach Pedersen","raw_affiliation_strings":["Aalborg University","[Aalborg university]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Aalborg university]","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"206"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9979000091552734,"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":0.9950000047683716,"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":0.8648161888122559},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7157537341117859},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6381746530532837},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.6245679259300232},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5479755401611328},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5461245775222778},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5382615327835083},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.45280882716178894},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3107025623321533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648161888122559},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7157537341117859},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6381746530532837},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6245679259300232},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5479755401611328},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5461245775222778},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5382615327835083},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.45280882716178894},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3107025623321533}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2628194.2628249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628194.2628249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Database Engineering &amp; Applications Symposium on - IDEAS '14","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/7bfcaeff-1314-4300-b064-6dd1a280375e","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/7bfcaeff-1314-4300-b064-6dd1a280375e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, X, Thomsen, C & Pedersen, T B 2014, CloudETL : Scalable Dimensional ETL for Hive. in Proceedings of the 18th International Database Engineering & Applications Symposium . Association for Computing Machinery (ACM), pp. 195-206, International Database Engineering & Applications Symposium, Porto, Portugal, 07/07/2014. https://doi.org/10.1145/2628194.2628249","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1486285670","https://openalex.org/W2010279913","https://openalex.org/W2035543557","https://openalex.org/W2038685484","https://openalex.org/W2043099794","https://openalex.org/W2044490410","https://openalex.org/W2075620950","https://openalex.org/W2078783226","https://openalex.org/W2083755493","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2102294813","https://openalex.org/W2110086534","https://openalex.org/W2114303224","https://openalex.org/W2125520775","https://openalex.org/W2125775320","https://openalex.org/W2126399065","https://openalex.org/W2152236140","https://openalex.org/W2158275487","https://openalex.org/W2170634549","https://openalex.org/W2171668176","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W4237177615","https://openalex.org/W2015567081","https://openalex.org/W2289257917"],"abstract_inverted_index":{"Extract-Transform-Load":[0],"(ETL)":[1],"programs":[2],"process":[3,123,132],"data":[4,6,11,31,94,124,174],"into":[5,125],"warehouses":[7],"(DWs).":[8],"Rapidly":[9],"growing":[10],"volumes":[12],"demand":[13],"systems":[14],"that":[15,195],"scale":[16],"out.":[17],"Recently,":[18],"much":[19],"attention":[20],"has":[21],"been":[22],"given":[23],"to":[24,56,77,85,117,122,144,177,211,224],"MapReduce":[25,47,97,148],"for":[26,44,80,93],"parallel":[27],"handling":[28],"of":[29,67,135,206],"massive":[30],"sets":[32],"in":[33,228],"cloud":[34],"environments.":[35],"Hive":[36,207,218],"is":[37,72],"the":[38,65,89,110,130,202],"most":[39],"widely":[40],"used":[41],"RDBMS-like":[42],"system":[43],"DWs":[45],"on":[46,96],"and":[48,121,138,140,159,166,186,200,213,231],"provides":[49],"scalable":[50],"analytics.":[51],"It":[52],"is,":[53],"however,":[54],"challenging":[55],"do":[57],"proper":[58],"dimensional":[59,102,153,203],"ETL":[60,103,111,119,131,204],"processing":[61,95],"with":[62,188,209],"Hive;":[63],"e.g.,":[64],"concept":[66],"slowly":[68],"changing":[69],"dimensions":[70],"(SCDs)":[71],"not":[73,99,142],"supported":[74],"(and":[75],"due":[76],"lacking":[78],"support":[79,100],"UPDATEs,":[81],"SCDs":[82],"are":[83],"complex":[84],"handle":[86],"manually).":[87],"Also":[88],"powerful":[90],"Pig":[91],"platform":[92],"does":[98,141],"such":[101,155],"processing.":[104],"To":[105],"remedy":[106],"this,":[107],"we":[108,181],"present":[109,162,182],"framework":[112],"CloudETL":[113,150,164,196,236],"which":[114],"uses":[115,167,219],"Hadoop":[116],"parallelize":[118],"execution":[120],"Hive.":[126],"The":[127,192],"user":[128],"defines":[129],"by":[133],"means":[134],"high-level":[136],"constructs":[137],"transformations":[139],"have":[143],"worry":[145],"about":[146],"technical":[147],"details.":[149],"supports":[151],"different":[152,168],"concepts":[154],"as":[156,222],"star":[157],"schemas":[158],"SCDs.":[160],"We":[161],"how":[163],"works":[165],"performance":[169,184,212],"optimizations":[170],"including":[171],"a":[172,183],"purpose-specific":[173],"placement":[175],"policy":[176],"co-locate":[178],"data.":[179],"Further,":[180],"study":[185],"compare":[187],"other":[189],"cloud-enabled":[190],"systems.":[191],"results":[193],"show":[194],"scales":[197],"very":[198],"well":[199],"outperforms":[201],"capabilities":[205],"both":[208],"respect":[210],"programmer":[214],"productivity.":[215],"For":[216],"example,":[217],"3.9":[220],"times":[221],"long":[223],"load":[225],"an":[226,229],"SCD":[227],"experiment":[230],"needs":[232,238],"112":[233],"statements":[234],"while":[235],"only":[237],"4.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
