{"id":"https://openalex.org/W2074846243","doi":"https://doi.org/10.1109/bigdata.2014.7004242","title":"Provenance-based object storage prediction scheme for scientific big data applications","display_name":"Provenance-based object storage prediction scheme for scientific big data applications","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2074846243","doi":"https://doi.org/10.1109/bigdata.2014.7004242","mag":"2074846243"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big 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/A5012002926","display_name":"Dong Dai","orcid":"https://orcid.org/0000-0003-4078-8149"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Dai","raw_affiliation_strings":["Computer Science Department, Texas Tech University","[Computer Science Department, Texas Tech University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Texas Tech University","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"[Computer Science Department, Texas Tech University]","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077521546","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-9961-9051"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Computer Science Department, Texas Tech University","[Computer Science Department, Texas Tech University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Texas Tech University","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"[Computer Science Department, Texas Tech University]","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058531444","display_name":"Dries Kimpe","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dries Kimpe","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory","Mathematics and Computer Science Division, Argonne National Laboratory#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory#TAB#","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036808423","display_name":"Robert Ross","orcid":"https://orcid.org/0000-0002-5435-5857"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Ross","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory","Mathematics and Computer Science Division, Argonne National Laboratory#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory#TAB#","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0584,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96907054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2003","issue":null,"first_page":"271","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9984999895095825,"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":0.9976999759674072,"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":0.849898099899292},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7189818620681763},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.678502082824707},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6136850118637085},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5620335340499878},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5302426815032959},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5135390758514404},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.45382699370384216},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.42981356382369995},{"id":"https://openalex.org/keywords/object-storage","display_name":"Object storage","score":0.4117283821105957},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35078704357147217},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34363269805908203},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3410445749759674},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17283591628074646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15100431442260742},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10936182737350464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849898099899292},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7189818620681763},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.678502082824707},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6136850118637085},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5620335340499878},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5302426815032959},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5135390758514404},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.45382699370384216},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.42981356382369995},{"id":"https://openalex.org/C56640594","wikidata":"https://www.wikidata.org/wiki/Q7075068","display_name":"Object storage","level":3,"score":0.4117283821105957},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35078704357147217},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34363269805908203},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3410445749759674},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17283591628074646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15100431442260742},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10936182737350464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W9857082","https://openalex.org/W25727798","https://openalex.org/W26797728","https://openalex.org/W67597731","https://openalex.org/W95542644","https://openalex.org/W168132470","https://openalex.org/W1516720694","https://openalex.org/W1559528097","https://openalex.org/W1814217792","https://openalex.org/W1816282546","https://openalex.org/W1858703999","https://openalex.org/W1976306141","https://openalex.org/W1983704199","https://openalex.org/W1999984505","https://openalex.org/W2010628428","https://openalex.org/W2027172230","https://openalex.org/W2058651674","https://openalex.org/W2070005502","https://openalex.org/W2072830823","https://openalex.org/W2096219499","https://openalex.org/W2110298485","https://openalex.org/W2115466528","https://openalex.org/W2120298634","https://openalex.org/W2128226234","https://openalex.org/W2131894525","https://openalex.org/W2156095355","https://openalex.org/W2162773908","https://openalex.org/W3005250903","https://openalex.org/W4229963820","https://openalex.org/W4251175597","https://openalex.org/W6600399817","https://openalex.org/W6602741087","https://openalex.org/W6603865566","https://openalex.org/W6606869816","https://openalex.org/W6638528845","https://openalex.org/W6650418438","https://openalex.org/W6679481876"],"related_works":["https://openalex.org/W2080470135","https://openalex.org/W2378855816","https://openalex.org/W4327907098","https://openalex.org/W2370205011","https://openalex.org/W2021496484","https://openalex.org/W4200525460","https://openalex.org/W3091659290","https://openalex.org/W1546463374","https://openalex.org/W1516720694","https://openalex.org/W2548311765"],"abstract_inverted_index":{"Object":[0],"storage":[1],"has":[2],"been":[3],"increasingly":[4],"adopted":[5],"in":[6,43,99,118,122,159],"high-performance":[7,119],"computing":[8,120],"for":[9,49,115,186],"scientific,":[10],"big":[11],"data":[12,28,40,116],"applications.":[13],"With":[14],"object":[15,20,35,160],"storage,":[16],"applications":[17,72],"usually":[18],"use":[19,108,156],"IDs,":[21],"queries,":[22],"or":[23,59],"collections":[24],"to":[25,54,124,142,155,162],"identify":[26],"the":[27,34,38,68,107,153,169,180],"instead":[29],"of":[30,70,109,173],"using":[31],"files.":[32],"Since":[33],"store":[36],"changes":[37],"way":[39],"is":[41,66,152,184],"accessed":[42],"applications,":[44],"it":[45],"introduces":[46],"new":[47],"challenges":[48],"I/O":[50],"prediction,":[51],"which":[52,112],"used":[53],"work":[55,97],"based":[56],"on":[57],"interfile":[58],"intrafile":[60],"pattern":[61],"detection.":[62],"The":[63,132],"key":[64],"challenge":[65],"that":[67,179],"inputs":[69],"object-based":[71],"are":[73],"no":[74],"longer":[75],"expressed":[76],"as":[77],"static":[78],"file":[79],"names:":[80],"they":[81],"become":[82],"much":[83],"more":[84],"dynamic":[85],"and":[86,171,177],"unstable,":[87],"hidden":[88],"inside":[89],"application":[90,164],"logic.":[91],"Traditional":[92],"prediction":[93,133,176,182],"strategies":[94],"do":[95],"not":[96],"well":[98],"such":[100],"conditions.":[101],"In":[102],"this":[103,150],"paper,":[104],"we":[105],"introduce":[106],"provenance":[110,157],"information,":[111],"was":[113],"collected":[114],"management":[117],"systems,":[121],"order":[123],"build":[125],"an":[126],"accurate":[127],"coarse-grained":[128],"(object-level)":[129],"input":[130],"prediction.":[131],"results":[134,167],"can":[135],"be":[136],"preloaded":[137],"into":[138],"a":[139],"burst":[140],"buffer":[141],"accelerate":[143],"future":[144],"reads.":[145],"To":[146],"our":[147,174],"best":[148],"knowledge,":[149],"study":[151],"first":[154],"information":[158],"stores":[161],"predict":[163],"inputs.":[165],"Evaluation":[166],"confirm":[168],"effectiveness":[170],"accuracy":[172],"provenance-based":[175],"show":[178],"proposed":[181],"system":[183],"feasible":[185],"real-work":[187],"deployment.":[188]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}