{"id":"https://openalex.org/W2558192069","doi":"https://doi.org/10.1109/tbdata.2016.2632744","title":"Speed Up Big Data Analytics by Unveiling the Storage Distribution of Sub-Datasets","display_name":"Speed Up Big Data Analytics by Unveiling the Storage Distribution of Sub-Datasets","publication_year":2016,"publication_date":"2016-11-29","ids":{"openalex":"https://openalex.org/W2558192069","doi":"https://doi.org/10.1109/tbdata.2016.2632744","mag":"2558192069"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2016.2632744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2016.2632744","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-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/A5100384682","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0926-4761"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL"],"raw_orcid":"https://orcid.org/0000-0002-0926-4761","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722406","display_name":"Xuhong Zhang","orcid":"https://orcid.org/0000-0002-8571-9780"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuhong Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100998670","display_name":"Jiangling Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiangling Yin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617182","display_name":"Ruijun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijun Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011637560","display_name":"Huafeng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Wu","raw_affiliation_strings":["College of Information Engineering, Shanghai Maritime University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101744803","display_name":"Dezhi Han","orcid":"https://orcid.org/0000-0001-8861-5461"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Han","raw_affiliation_strings":["College of Information Engineering, Shanghai Maritime University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9831,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88525876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"2","first_page":"231","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11478","display_name":"Caching and Content Delivery","score":0.9994000196456909,"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":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8985928297042847},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7388930320739746},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.624454140663147},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6063386797904968},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5753622055053711},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5136122703552246},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.47663769125938416},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4760070741176605},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45974403619766235},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4254201352596283},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.42318400740623474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12678208947181702},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09828701615333557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8985928297042847},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7388930320739746},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.624454140663147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6063386797904968},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5753622055053711},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5136122703552246},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.47663769125938416},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4760070741176605},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45974403619766235},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4254201352596283},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.42318400740623474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12678208947181702},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09828701615333557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2016.2632744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2016.2632744","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4454591167","display_name":null,"funder_award_id":"51279099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8303540275","display_name":"\u57fa\u4e8e\u6d77\u6d6a\u906e\u853d\u6548\u5e94\u6a21\u578b\u7684\u6d77\u6d0b\u4f20\u611f\u7f51\u4e09\u7ef4\u52a8\u6001\u534f\u540c\u5b9a\u4f4d\u673a\u5236","funder_award_id":"51579143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321883","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53"},{"id":"https://openalex.org/F4320326300","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66"},{"id":"https://openalex.org/F4320328099","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W16186195","https://openalex.org/W1441763937","https://openalex.org/W1503025338","https://openalex.org/W1598064945","https://openalex.org/W1602474204","https://openalex.org/W1876812886","https://openalex.org/W1969891822","https://openalex.org/W1989269499","https://openalex.org/W1990285714","https://openalex.org/W1995900733","https://openalex.org/W2000832852","https://openalex.org/W2007333650","https://openalex.org/W2009858916","https://openalex.org/W2020133428","https://openalex.org/W2021112138","https://openalex.org/W2034960202","https://openalex.org/W2048334074","https://openalex.org/W2061303007","https://openalex.org/W2073897588","https://openalex.org/W2080131844","https://openalex.org/W2099216531","https://openalex.org/W2116166888","https://openalex.org/W2123845384","https://openalex.org/W2129374565","https://openalex.org/W2140509629","https://openalex.org/W2150915951","https://openalex.org/W2184628147","https://openalex.org/W2215904967","https://openalex.org/W2287880243","https://openalex.org/W2339613164","https://openalex.org/W2506214730","https://openalex.org/W2545764389","https://openalex.org/W2995564009","https://openalex.org/W4255821617","https://openalex.org/W4372046852","https://openalex.org/W6600634475","https://openalex.org/W6628361010","https://openalex.org/W6635833716","https://openalex.org/W6639324668","https://openalex.org/W6686265631","https://openalex.org/W6695856656"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W4285042611","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,121,134,154],"study":[4],"the":[5,15,23,50,128,144,151,190,193],"problem":[6],"of":[7,53,73,83,130,196],"sub-dataset":[8,110,131,159,174],"analysis":[9,76,90,111],"over":[10,26,112],"distributed":[11,113],"file":[12,17],"systems,":[13],"e.g.,":[14],"Hadoop":[16],"system.":[18],"Our":[19,168],"experiments":[20],"show":[21,192],"that":[22],"sub-datasets":[24,54],"distribution":[25,105],"HDFS":[27],"blocks,":[28],"which":[29],"is":[30],"hidden":[31],"by":[32],"HDFS,":[33],"can":[34,171],"often":[35,79],"cause":[36],"corresponding":[37],"analyses":[38,175],"to":[39,70,108,117,126,149,161],"suffer":[40],"from":[41],"a":[42,88,103],"seriously":[43],"imbalanced":[44,93],"or":[45],"inefficient":[46,71,97],"parallel":[47,166],"execution.":[48,167],"Specifically,":[49],"content":[51],"clustering":[52],"results":[55,191],"in":[56],"some":[57],"computational":[58,178],"nodes":[59],"carrying":[60],"out":[61],"much":[62],"more":[63],"workload":[64],"than":[65],"others;":[66],"furthermore,":[67],"it":[68],"leads":[69],"sampling":[72,98],"sub-datasets,":[74],"as":[75,118],"programs":[77],"will":[78],"read":[80],"large":[81],"amounts":[82],"irrelevant":[84],"data.":[85],"We":[86,100],"conduct":[87],"comprehensive":[89],"on":[91,143,183],"how":[92],"computing":[94],"patterns":[95],"and":[96,146,164,189],"occur.":[99],"then":[101],"propose":[102,122],"storage":[104,114,138],"aware":[106],"method":[107,170],"optimize":[109],"systems":[115],"referred":[116],"DataNet.":[119,197],"First,":[120],"an":[123,136],"efficient":[124,165],"algorithm":[125],"obtain":[127],"meta-data":[129],"distributions.":[132],"Second,":[133],"design":[135],"elastic":[137],"structure":[139],"called":[140],"ElasticMap":[141],"based":[142],"HashMap":[145],"BloomFilter":[147],"techniques":[148],"store":[150],"meta-data.":[152],"Third,":[153],"employ":[155],"distribution-aware":[156],"algorithms":[157],"for":[158],"applications":[160],"achieve":[162],"balanced":[163],"proposed":[169],"benefit":[172],"different":[173],"with":[176],"various":[177],"requirements.":[179],"Experiments":[180],"are":[181],"conducted":[182],"PRObEs":[184],"Marmot":[185],"128-node":[186],"cluster":[187],"testbed":[188],"performance":[194],"benefits":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"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":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}