{"id":"https://openalex.org/W2885605495","doi":"https://doi.org/10.1145/3150928.3150943","title":"Runtime Performance Prediction of Big Data Workflows with I/O-aware Simulation","display_name":"Runtime Performance Prediction of Big Data Workflows with I/O-aware Simulation","publication_year":2017,"publication_date":"2017-12-05","ids":{"openalex":"https://openalex.org/W2885605495","doi":"https://doi.org/10.1145/3150928.3150943","mag":"2885605495"},"language":"en","primary_location":{"id":"doi:10.1145/3150928.3150943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3150928.3150943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th EAI International Conference on Performance Evaluation Methodologies and Tools","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/A5004031081","display_name":"Faris Llwaah","orcid":null},"institutions":[{"id":"https://openalex.org/I12150220","display_name":"University of Mosul","ror":"https://ror.org/039cf4q47","country_code":"IQ","type":"education","lineage":["https://openalex.org/I12150220"]}],"countries":["IQ"],"is_corresponding":true,"raw_author_name":"Faris Llwaah","raw_affiliation_strings":["School of Computing Science, Newcastle University, College of Computer Sciences and Mathematics, Mosul University, Iraq"],"affiliations":[{"raw_affiliation_string":"School of Computing Science, Newcastle University, College of Computer Sciences and Mathematics, Mosul University, Iraq","institution_ids":["https://openalex.org/I12150220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052190130","display_name":"Jacek Ca\u0142a","orcid":"https://orcid.org/0000-0002-8322-4370"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jacek Ca\u0142a","raw_affiliation_strings":["School of Computing Science, Newcastle University"],"affiliations":[{"raw_affiliation_string":"School of Computing Science, Newcastle University","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010768909","display_name":"Nigel Thomas","orcid":"https://orcid.org/0000-0002-0844-6838"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nigel Thomas","raw_affiliation_strings":["School of Computing Science, Newcastle University"],"affiliations":[{"raw_affiliation_string":"School of Computing Science, Newcastle University","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004031081"],"corresponding_institution_ids":["https://openalex.org/I12150220"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36203608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"371","issue":null,"first_page":"74","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"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":0.9970999956130981,"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":0.8462949991226196},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.837643027305603},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6877614855766296},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6422646045684814},{"id":"https://openalex.org/keywords/cloudsim","display_name":"CloudSim","score":0.5838796496391296},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5608584880828857},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.508377730846405},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43941938877105713},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4376615285873413},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43362778425216675},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.42739367485046387},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40650463104248047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16973450779914856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8462949991226196},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.837643027305603},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6877614855766296},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6422646045684814},{"id":"https://openalex.org/C2779907789","wikidata":"https://www.wikidata.org/wiki/Q22095616","display_name":"CloudSim","level":3,"score":0.5838796496391296},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5608584880828857},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.508377730846405},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43941938877105713},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4376615285873413},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43362778425216675},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.42739367485046387},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40650463104248047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16973450779914856},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3150928.3150943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3150928.3150943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th EAI International Conference on Performance Evaluation Methodologies and Tools","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1621944069","https://openalex.org/W1817903323","https://openalex.org/W1978802375","https://openalex.org/W1986421100","https://openalex.org/W2029467255","https://openalex.org/W2043502750","https://openalex.org/W2045287414","https://openalex.org/W2049449935","https://openalex.org/W2103128343","https://openalex.org/W2126160525","https://openalex.org/W2129666400","https://openalex.org/W2148459868","https://openalex.org/W2149140091","https://openalex.org/W2282327192","https://openalex.org/W2292609951","https://openalex.org/W2398293162","https://openalex.org/W2519182983","https://openalex.org/W2537715700","https://openalex.org/W2911567575"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Modelling":[0],"and":[1,32,40,57,127,142,161,177],"simulation":[2,78,121],"of":[3,26,43,61,76,87,103,110,144],"Big":[4,62],"Data":[5,63],"analytics":[6],"processes":[7,64],"running":[8],"in":[9,165],"the":[10,24,59,95,101,140,145,157,172],"cloud":[11,117],"is":[12,23,30,80,123],"a":[13,52,84,134],"difficult":[14],"problem":[15],"which":[16,29,130],"introduces":[17],"many":[18],"challenges.":[19],"The":[20,73,168],"major":[21,74],"one":[22],"collection":[25],"training":[27,96],"data":[28,91,118],"scarce":[31],"costly":[33],"to":[34,37,54,129,194],"obtain,":[35],"due":[36],"large":[38],"scale":[39],"long":[41],"runtime":[42,60,88],"those":[44],"processes.":[45],"In":[46],"our":[47,77,111,183],"previous":[48,112,195],"work,":[49],"we":[50,105,131],"proposed":[51,173],"methodology":[53,79],"model,":[55],"simulate":[56],"predict":[58],"such":[65],"as":[66],"complex":[67],"Next":[68],"Generation":[69],"Sequencing":[70],"(NGS)":[71],"pipelines.":[72],"contribution":[75],"that":[81,114,171],"it":[82],"provides":[83],"reasonable":[85],"prediction":[86,104,180],"for":[89,182],"testing":[90],"much":[92],"larger":[93],"than":[94],"inputs.":[97],"To":[98],"further":[99],"improve":[100,179],"accuracy":[102,181],"present":[106,139],"now":[107],"an":[108,150],"extension":[109,147,174],"work":[113],"can":[115,178],"model":[116],"storage.":[119],"Our":[120],"framework":[122],"based":[124],"on":[125,153],"CloudSim":[126],"WorkflowSim,":[128],"have":[132],"added":[133],"shared":[135],"storage":[136,146],"component.":[137],"We":[138],"design":[141],"implementation":[143],"together":[148],"with":[149],"evaluation":[151,169],"performed":[152],"selected":[154],"scientific":[155],"workflows:":[156],"Pegasus":[158],"Montage":[159],"workflow":[160],"NGS":[162],"pipeline":[163],"implemented":[164],"e-Science":[166],"Central.":[167],"shows":[170],"works":[175],"correctly":[176],"largest":[184],"390":[185],"GB":[186],"input":[187],"dataset":[188],"by":[189],"about":[190],"16%":[191],"when":[192],"compared":[193],"results.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}