{"id":"https://openalex.org/W3090251462","doi":"https://doi.org/10.1109/icccn49398.2020.9209715","title":"Performance Modeling and Prediction of Big Data Workflows: An Exploratory Analysis","display_name":"Performance Modeling and Prediction of Big Data Workflows: An Exploratory Analysis","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3090251462","doi":"https://doi.org/10.1109/icccn49398.2020.9209715","mag":"3090251462"},"language":"en","primary_location":{"id":"doi:10.1109/icccn49398.2020.9209715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn49398.2020.9209715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th International Conference on Computer Communications and Networks (ICCCN)","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/A5031393751","display_name":"Wuji Liu","orcid":"https://orcid.org/0000-0003-3213-5172"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wuji Liu","raw_affiliation_strings":["Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054307870","display_name":"Chase Q. Wu","orcid":"https://orcid.org/0000-0002-8218-1209"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Q. Wu","raw_affiliation_strings":["Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034932607","display_name":"Qianwen Ye","orcid":"https://orcid.org/0000-0001-9843-527X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianwen Ye","raw_affiliation_strings":["Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077422534","display_name":"Aiqin Hou","orcid":"https://orcid.org/0000-0002-5311-2431"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiqin Hou","raw_affiliation_strings":["School of Information Science and Technology, Northwest University, Xi\u2019an, China","School of Information Science and Technology, Northwest University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northwest University, Xi\u2019an, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"School of Information Science and Technology, Northwest University, Xi'an, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048353325","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0002-1235-598X"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["School of Informatics Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China","institution_ids":["https://openalex.org/I1328775524"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9089,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74975888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976999759674072,"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":0.9976999759674072,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9973999857902527,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9865999817848206,"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/workflow","display_name":"Workflow","score":0.8555104732513428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8532650470733643},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7841552495956421},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7445582151412964},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6775789856910706},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5705951452255249},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.5229737758636475},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.5212117433547974},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.49194857478141785},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44338858127593994},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3532046675682068},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34839653968811035},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.15830889344215393},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15475395321846008}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8555104732513428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532650470733643},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7841552495956421},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7445582151412964},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6775789856910706},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5705951452255249},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.5229737758636475},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.5212117433547974},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.49194857478141785},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44338858127593994},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3532046675682068},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34839653968811035},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.15830889344215393},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15475395321846008},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn49398.2020.9209715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn49398.2020.9209715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th International Conference on Computer Communications and Networks (ICCCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1798528872","https://openalex.org/W1966275653","https://openalex.org/W2003014979","https://openalex.org/W2051385358","https://openalex.org/W2055255737","https://openalex.org/W2072617662","https://openalex.org/W2100015718","https://openalex.org/W2101234009","https://openalex.org/W2125320251","https://openalex.org/W2129666400","https://openalex.org/W2130248252","https://openalex.org/W2146279585","https://openalex.org/W2157777898","https://openalex.org/W2163493291","https://openalex.org/W2175075972","https://openalex.org/W2210387432","https://openalex.org/W2500139799","https://openalex.org/W2529999572","https://openalex.org/W2560566187","https://openalex.org/W2578279218","https://openalex.org/W2584551900","https://openalex.org/W2946003964","https://openalex.org/W2963288913","https://openalex.org/W2993459617","https://openalex.org/W3159649695","https://openalex.org/W4252709122","https://openalex.org/W6614148910","https://openalex.org/W6675070369","https://openalex.org/W6675354045","https://openalex.org/W6679182976","https://openalex.org/W6679517723"],"related_works":["https://openalex.org/W2375304607","https://openalex.org/W2391168633","https://openalex.org/W2035995658","https://openalex.org/W2353477037","https://openalex.org/W3083262785","https://openalex.org/W1574425962","https://openalex.org/W2385499106","https://openalex.org/W4310820052","https://openalex.org/W2354357087","https://openalex.org/W2352774566"],"abstract_inverted_index":{"Many":[0],"next-generation":[1],"scientific":[2],"and":[3,28,63,88,97,163,177,183,206],"business":[4],"applications":[5],"feature":[6,116],"large-scale":[7],"data-intensive":[8],"workflows,":[9],"which":[10],"require":[11],"massive":[12],"computing":[13,24,130,161],"resources":[14,25],"for":[15,191,203],"execution":[16],"on":[17,124,180],"high-performance":[18],"clusters":[19],"in":[20,35,133,150,210],"cloud":[21],"environments.":[22],"Such":[23],"(e.g.,":[26],"VCores":[27],"virtual":[29],"memory)":[30],"requested":[31],"through":[32],"parameter":[33,75,95],"setting":[34],"big":[36,105,134,152],"data":[37,106,135,153],"systems,":[38],"if":[39],"not":[40],"fully":[41],"utilized":[42],"by":[43,57],"workloads,":[44],"are":[45],"simply":[46],"wasted":[47],"due":[48,91],"to":[49,68,77,84,92,119],"the":[50,93,98,151,197],"nature":[51],"of":[52,65,73,104,128,145,174],"exclusive":[53],"access":[54],"made":[55],"possible":[56],"containerization.":[58],"This":[59],"necessitates":[60],"accurate":[61],"modeling":[62,205],"prediction":[64],"workflow":[66,87,157,181],"performance":[67,126,204,211],"make":[69],"an":[70,170],"effective":[71],"recommendation":[72],"appropriate":[74],"settings":[76],"end":[78],"users.":[79],"However,":[80],"it":[81],"is":[82],"challenging":[83],"determine":[85],"optimal":[86],"system":[89],"configurations":[90],"large":[94],"space":[96],"interaction":[99],"between":[100],"various":[101],"technology":[102,154],"layers":[103,149],"systems.":[107],"Towards":[108],"this":[109],"goal,":[110],"we":[111],"propose":[112],"a":[113,142,185],"machine":[114],"learning-based":[115],"selection":[117],"method":[118],"identify":[120,141],"influential":[121],"parameters":[122,146],"based":[123],"historical":[125],"measurements":[127],"Spark-based":[129],"workloads":[131],"executed":[132],"systems":[136],"with":[137],"YARN.":[138],"We":[139,167],"first":[140],"comprehensive":[143],"set":[144],"across":[147],"multiple":[148],"stack":[155],"including":[156],"input":[158],"structure,":[159],"Spark":[160],"engine,":[162],"YARN":[164],"resource":[165],"management.":[166],"then":[168],"conduct":[169],"in-depth":[171],"exploratory":[172],"analysis":[173],"their":[175],"individual":[176],"coupled":[178],"impact":[179],"performance,":[182],"develop":[184],"performance-influence":[186],"model":[187],"using":[188],"random":[189],"forest":[190],"prediction.":[192,212],"Experimental":[193],"results":[194],"show":[195],"that":[196],"proposed":[198],"approach":[199],"identifies":[200],"important":[201],"features":[202],"achieves":[207],"high":[208],"accuracy":[209]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}