{"id":"https://openalex.org/W3006928522","doi":"https://doi.org/10.1109/bigdata47090.2019.9005543","title":"Analysis and Prediction of Data Transfer Throughput for Data-Intensive Workloads","display_name":"Analysis and Prediction of Data Transfer Throughput for Data-Intensive Workloads","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3006928522","doi":"https://doi.org/10.1109/bigdata47090.2019.9005543","mag":"3006928522"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9005543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5091593528","display_name":"Devarshi Ghoshal","orcid":"https://orcid.org/0000-0002-6819-6949"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devarshi Ghoshal","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043129695","display_name":"Kesheng Wu","orcid":"https://orcid.org/0000-0002-6907-3393"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kesheng Wu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078182995","display_name":"Eric Pouyoul","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Pouyoul","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060406684","display_name":"Erich Strohmaier","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erich Strohmaier","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7053,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81015077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"3648","last_page":"3657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9969000220298767,"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":0.9962000250816345,"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":0.8631001710891724},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6862258911132812},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5842938423156738},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5405042171478271},{"id":"https://openalex.org/keywords/file-transfer","display_name":"File transfer","score":0.5058331489562988},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49145567417144775},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.48746681213378906},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.47254419326782227},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.4359099566936493},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.4339671730995178},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.426086962223053},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.41236698627471924},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35536301136016846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2276022732257843},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1947265863418579},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1558108925819397},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1352216601371765},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.09637081623077393},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08881166577339172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631001710891724},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6862258911132812},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5842938423156738},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5405042171478271},{"id":"https://openalex.org/C2776162994","wikidata":"https://www.wikidata.org/wiki/Q534400","display_name":"File transfer","level":3,"score":0.5058331489562988},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49145567417144775},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.48746681213378906},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.47254419326782227},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.4359099566936493},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.4339671730995178},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.426086962223053},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.41236698627471924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35536301136016846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2276022732257843},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1947265863418579},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1558108925819397},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1352216601371765},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.09637081623077393},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08881166577339172},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9005543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1480875294","https://openalex.org/W1516506771","https://openalex.org/W1639019325","https://openalex.org/W1660433879","https://openalex.org/W1976381032","https://openalex.org/W2010644199","https://openalex.org/W2035004292","https://openalex.org/W2040356714","https://openalex.org/W2046612125","https://openalex.org/W2060209982","https://openalex.org/W2076226477","https://openalex.org/W2092829070","https://openalex.org/W2101109743","https://openalex.org/W2103758921","https://openalex.org/W2108377002","https://openalex.org/W2126345423","https://openalex.org/W2137632784","https://openalex.org/W2146176543","https://openalex.org/W2155979530","https://openalex.org/W2156712008","https://openalex.org/W2164837776","https://openalex.org/W2165855437","https://openalex.org/W2168400800","https://openalex.org/W2316327132","https://openalex.org/W2499705876","https://openalex.org/W2569784417","https://openalex.org/W2728176761","https://openalex.org/W2901743327","https://openalex.org/W2917440171","https://openalex.org/W2950139091","https://openalex.org/W4238971728","https://openalex.org/W4242330541","https://openalex.org/W4244859942","https://openalex.org/W6637317073"],"related_works":["https://openalex.org/W2370299118","https://openalex.org/W2765314983","https://openalex.org/W2135470163","https://openalex.org/W4291639629","https://openalex.org/W2963042525","https://openalex.org/W2771869459","https://openalex.org/W2366416741","https://openalex.org/W2124597432","https://openalex.org/W2136671438","https://openalex.org/W2364074001"],"abstract_inverted_index":{"Scientific":[0],"workflows":[1],"are":[2,20],"increasingly":[3],"transferring":[4],"large":[5],"amounts":[6],"of":[7,44,53,102,141,192],"data":[8,29,40,47,78,104,151,194],"between":[9],"high":[10,176],"performance":[11,52,64,99,191],"computing":[12],"(HPC)":[13],"systems.":[14],"Even":[15],"though":[16],"these":[17],"HPC":[18,166],"systems":[19],"connected":[21],"via":[22],"high-speed":[23],"dedicated":[24,28],"networks":[25],"and":[26,56,70,100,168,183],"use":[27,133],"transfer":[30,41,48,79,105],"nodes":[31],"(DTNs),":[32],"it":[33],"is":[34],"still":[35],"difficult":[36],"to":[37,61,97,109,123,137,185],"predict":[38,173],"the":[39,110,115,129,134,139,147,190],"throughput":[42,80,148,174],"because":[43],"variations":[45,163],"in":[46,145],"protocols,":[49],"host":[50],"configurations,":[51],"file":[54],"systems,":[55],"overlapping":[57],"workloads.":[58],"In":[59,84,107],"order":[60],"provide":[62,186],"reliable":[63],"prediction":[65,101,130,135],"for":[66,76,93,127,149,188],"better":[67],"resource":[68],"management":[69],"job":[71],"scheduling,":[72],"we":[73,87,119,156,171],"need":[74],"models":[75,96,182],"predicting":[77,146],"under":[81],"real-world":[82],"conditions.":[83],"this":[85],"paper,":[86],"explore":[88],"different":[89,142,165],"machine":[90],"learning":[91],"approaches":[92],"building":[94],"data-driven":[95],"improve":[98],"large-scale":[103,150],"throughput.":[106],"addition":[108],"variables":[111],"already":[112],"collected":[113],"by":[114],"network":[116,143,159],"monitoring":[117],"system,":[118],"also":[120,179],"develop":[121],"heuristics":[122],"derive":[124],"additional":[125],"metrics":[126],"improving":[128,189],"accuracy.":[131,177],"We":[132,178],"results":[136,184],"identify":[138,157],"importance":[140],"parameters":[144],"transfers.":[152,195],"Through":[153],"extensive":[154],"tests,":[155],"key":[158],"parameters,":[160],"discover":[161],"interesting":[162],"among":[164],"sites,":[167],"show":[169],"that":[170],"can":[172],"with":[175],"analyze":[180],"our":[181],"recommendations":[187],"big":[193]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}