{"id":"https://openalex.org/W2584596691","doi":null,"title":"Development of Best Practices for Large-scale Data Management Infrastructure","display_name":"Development of Best Practices for Large-scale Data Management Infrastructure","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2584596691","mag":"2584596691"},"language":"en","primary_location":{"id":"pmh:cwi:oai:cwi.nl:20508","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/20508","pdf_url":"https://ir.cwi.nl/pub/20508","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"info:eu-repo/semantics/other"},"volume":null,"type":"other","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/20508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007378564","display_name":"Steffen Stadtm\u00fcller","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steffen Stadtm\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050785612","display_name":"Hannes M\u00fchleisen","orcid":"https://orcid.org/0000-0001-8552-0029","observed_orcids":["https://orcid.org/0000-0001-8552-0029"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hannes M\u00fchleisen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8552-0029","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074202535","display_name":"Chris Bizer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Bizer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108572275","display_name":"Martin L. Kersten","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Kersten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150315815","display_name":"Arjen Rijke","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arjen de Rijke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083976181","display_name":"Fabian Groffen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Groffen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386224","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0003-1620-3825","observed_orcids":["https://orcid.org/0000-0003-1620-3825"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1620-3825","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113656807","display_name":"G\u00fcnter Ladwig","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00fcnter Ladwig","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033280983","display_name":"Andreas Harth","orcid":"https://orcid.org/0000-0002-0702-510X","observed_orcids":["https://orcid.org/0000-0002-0702-510X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Harth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050714793","display_name":"Mitja Trampu\u0161","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitja Trampu\u0161","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9473000168800354,"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":0.9473000168800354,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.03020000085234642,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.009499999694526196,"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/large-scale-data-management","display_name":"large-scale data management","score":0.9919999837875366},{"id":"https://openalex.org/keywords/hadoop","display_name":"Hadoop","score":0.8379999995231628},{"id":"https://openalex.org/keywords/cluster-computing","display_name":"cluster computing","score":0.7850000262260437},{"id":"https://openalex.org/keywords/cloud-storage","display_name":"cloud storage","score":0.5870000123977661},{"id":"https://openalex.org/keywords/microformats","display_name":"microformats","score":0.7250000238418579},{"id":"https://openalex.org/keywords/microdata","display_name":"microdata","score":0.9800000190734863},{"id":"https://openalex.org/keywords/rdfa","display_name":"RDFa","score":0.9990000128746033},{"id":"https://openalex.org/keywords/common-crawl","display_name":"Common Crawl","score":0.968999981880188},{"id":"https://openalex.org/keywords/rdf-stores","display_name":"RDF stores","score":0.8809999823570251},{"id":"https://openalex.org/keywords/linked-data","display_name":"linked data","score":0.6629999876022339},{"id":"https://openalex.org/keywords/distributed-key-value-store","display_name":"distributed key-value store","score":0.718999981880188},{"id":"https://openalex.org/keywords/best-practices","display_name":"best practices","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980581521987915},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6400591135025024},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5828627943992615},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4947654604911804},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.485710471868515},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45883554220199585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4380561411380768},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4265727996826172},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4167781174182892},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37744566798210144},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3116260766983032},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.22336333990097046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16675463318824768}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:cwi:oai:cwi.nl:20508","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/20508","pdf_url":"https://ir.cwi.nl/pub/20508","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"info:eu-repo/semantics/other"},{"id":"pmh:oai:cwi.nl:20508","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/20508","pdf_url":"https://ir.cwi.nl/pub/20508/20508D.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/other"},{"id":"mag:2584596691","doi":null,"is_oa":false,"landing_page_url":"https://ir.cwi.nl/pub/20508/20508D.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:cwi:oai:cwi.nl:20508","doi":null,"is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/20508","pdf_url":"https://ir.cwi.nl/pub/20508","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2584596691.pdf","grobid_xml":"https://content.openalex.org/works/W2584596691.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W56918557","https://openalex.org/W102708294","https://openalex.org/W1544119352","https://openalex.org/W1548849615","https://openalex.org/W1937427849","https://openalex.org/W1964941055","https://openalex.org/W1972793074","https://openalex.org/W1983094331","https://openalex.org/W1990080756","https://openalex.org/W2084961399","https://openalex.org/W2089247435","https://openalex.org/W2113640782","https://openalex.org/W2120101509","https://openalex.org/W2129412326","https://openalex.org/W2135577024","https://openalex.org/W2140208587","https://openalex.org/W2140613126","https://openalex.org/W2148522916","https://openalex.org/W2153704625","https://openalex.org/W2161131159","https://openalex.org/W2161291780","https://openalex.org/W2167149779","https://openalex.org/W2173213060","https://openalex.org/W2183157053","https://openalex.org/W2262562434","https://openalex.org/W2284530523","https://openalex.org/W2293919922","https://openalex.org/W2339861584","https://openalex.org/W2520948221","https://openalex.org/W2571426820","https://openalex.org/W2624304035"],"related_works":["https://openalex.org/W2476006766","https://openalex.org/W2768052570","https://openalex.org/W2007855128","https://openalex.org/W2500108018","https://openalex.org/W2069583953","https://openalex.org/W4321843809","https://openalex.org/W2952032245","https://openalex.org/W2987196290","https://openalex.org/W14948144","https://openalex.org/W3130415755"],"abstract_inverted_index":{"The":[0,106],"amount":[1],"of":[2,47,63,100,172,196,210,216,233],"available":[3,137],"data":[4,21,58,103,120,154],"for":[5,111,157,184,192,227],"processing":[6,222],"is":[7,135,207],"constantly":[8],"increasing":[9],"and":[10,30,37,67,98,118,129,230],"becomes":[11],"more":[12],"diverse.":[13],"We":[14,168],"collect":[15],"our":[16,87],"experiences":[17,88],"on":[18,24,61,70,86,153,165],"deploying":[19],"large-scale":[20,81],"management":[22,104,155],"tools":[23],"local-area":[25,143],"clusters":[26,62],"or":[27],"cloud":[28],"infrastructures":[29],"provide":[31,68,92],"guidance":[32,69],"to":[33,54,72,138,150,212],"use":[34,99],"these":[35],"computing":[36],"storage":[38,182],"infrastructures.":[39],"In":[40],"particular":[41],"we":[42,84,113,200],"describe":[43,201],"Apache":[44],"Hadoop,":[45],"one":[46],"the":[48,96,122,127,139,170,202,214,231,234],"most":[49,130],"widely":[50],"used":[51],"software":[52,211],"libraries":[53],"perform":[55,213],"large-":[56,101],"scale":[57,102],"analysis":[59,79,229],"tasks":[60],"computers":[64],"in":[65,95],"parallel":[66],"how":[71],"achieve":[73],"optimal":[74],"execution":[75],"time":[76],"when":[77],"performing":[78],"over":[80],"data.":[82,235],"Furthermore":[83],"report":[85],"with":[89],"projects,":[90],"that":[91,134,146],"valuable":[93],"insights":[94],"deployment":[97],"tools:":[105],"Web":[107],"Data":[108,187],"Commons":[109],"project":[110],"which":[112,189,206],"extracted":[114],"all":[115],"Microformat,":[116],"Microdata":[117],"RDFa":[119],"from":[121],"Common":[123],"Crawl":[124],"web":[125,132],"corpus,":[126],"largest":[128],"up-to-date":[131],"corpus":[133],"currently":[136],"public.":[140],"SciLens,":[141],"a":[142,174,185,208,224],"cluster":[144],"machine":[145],"has":[147],"been":[148],"built":[149],"facilitate":[151],"research":[152],"issues":[156],"data-intensive":[158],"scientific":[159],"applications.":[160],"CumulusRDF,":[161],"an":[162,180],"RDF":[163],"store":[164,178],"cloud-based":[166],"architectures.":[167],"investigate":[169],"feasibility":[171],"using":[173],"distributed":[175],"nested":[176],"key/value":[177],"as":[179],"underlying":[181],"component":[183],"Linked":[186,197],"server,":[188],"provides":[190],"functionality":[191],"serving":[193],"large":[194],"quantities":[195],"Data.":[198],"Finally":[199],"News":[203],"Aggregator":[204],"Pipeline,":[205],"piece":[209],"acquisition":[215],"high":[217],"volume":[218],"textual":[219],"streams,":[220],"it\u2019s":[221],"into":[223],"suitable":[225],"form":[226],"further":[228],"distribution":[232]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-02-10T00:00:00"}