{"id":"https://openalex.org/W3009370840","doi":"https://doi.org/10.23919/cnsm46954.2019.9012752","title":"Quick Execution Time Predictions for Spark Applications","display_name":"Quick Execution Time Predictions for Spark Applications","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3009370840","doi":"https://doi.org/10.23919/cnsm46954.2019.9012752","mag":"3009370840"},"language":"en","primary_location":{"id":"doi:10.23919/cnsm46954.2019.9012752","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm46954.2019.9012752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Conference on Network and Service Management (CNSM)","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/A5049988473","display_name":"Sarah Shah","orcid":"https://orcid.org/0000-0003-0627-7070"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sarah Shah","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Calgary, Calgary, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Calgary, Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086312071","display_name":"Yasaman Amannejad","orcid":"https://orcid.org/0000-0002-5668-6086"},"institutions":[{"id":"https://openalex.org/I870124129","display_name":"Mount Royal University","ror":"https://ror.org/04evsam41","country_code":"CA","type":"education","lineage":["https://openalex.org/I870124129"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yasaman Amannejad","raw_affiliation_strings":["Department of Mathematics and Computing, Mount Royal University, Calgary, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computing, Mount Royal University, Calgary, Canada","institution_ids":["https://openalex.org/I870124129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001117576","display_name":"Diwakar Krishnamurthy","orcid":"https://orcid.org/0000-0002-6098-4801"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Diwakar Krishnamurthy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Calgary, Calgary, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Calgary, Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020669873","display_name":"Mea Wang","orcid":"https://orcid.org/0000-0001-8400-9069"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mea Wang","raw_affiliation_strings":["Department of Computer Science, University of Calgary, Calgary, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Calgary, Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049988473"],"corresponding_institution_ids":["https://openalex.org/I168635309"],"apc_list":null,"apc_paid":null,"fwci":6.1047,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96613103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9936000108718872,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/spark","display_name":"SPARK (programming language)","score":0.9432731866836548},{"id":"https://openalex.org/keywords/executor","display_name":"Executor","score":0.8731975555419922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.847630500793457},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6511648893356323},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6204821467399597},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5409882664680481},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.5356431007385254},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4755518138408661},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4589484930038452},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4577537775039673},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37056612968444824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3249845504760742},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24309122562408447}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9432731866836548},{"id":"https://openalex.org/C180591056","wikidata":"https://www.wikidata.org/wiki/Q654437","display_name":"Executor","level":2,"score":0.8731975555419922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847630500793457},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6511648893356323},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6204821467399597},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5409882664680481},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.5356431007385254},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4755518138408661},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4589484930038452},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4577537775039673},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37056612968444824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3249845504760742},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24309122562408447},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/cnsm46954.2019.9012752","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm46954.2019.9012752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Conference on Network and Service Management (CNSM)","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":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1899447984","https://openalex.org/W2150871235","https://openalex.org/W2175075972","https://openalex.org/W2309679942","https://openalex.org/W2488300951","https://openalex.org/W2528415359","https://openalex.org/W2570373436","https://openalex.org/W2573911191","https://openalex.org/W2582789036","https://openalex.org/W2770935003","https://openalex.org/W2776147949","https://openalex.org/W2796039710","https://openalex.org/W2809559041","https://openalex.org/W2970105940","https://openalex.org/W4292666002","https://openalex.org/W6697698479","https://openalex.org/W6722756077","https://openalex.org/W6727576777","https://openalex.org/W6747615343"],"related_works":["https://openalex.org/W2603352950","https://openalex.org/W4241425178","https://openalex.org/W4246956338","https://openalex.org/W3191926225","https://openalex.org/W3195722949","https://openalex.org/W4246264554","https://openalex.org/W2962431048","https://openalex.org/W3112375919","https://openalex.org/W4322731236","https://openalex.org/W4233648438"],"abstract_inverted_index":{"The":[0,183],"Apache":[1],"Spark":[2,31,40,70,100,124,278,288],"cluster":[3,41,159],"computing":[4],"platform":[5],"is":[6,54,234],"being":[7],"increasingly":[8],"used":[9,235],"to":[10,56,63,80,96,118,167,212,236,269],"develop":[11],"big":[12],"data":[13,79,141,231,253],"analytics":[14],"applications.":[15],"There":[16],"are":[17,146,154,161],"many":[18],"scenarios":[19],"that":[20,92,179,241,257,294],"require":[21,43,129],"quick":[22,44,152],"estimates":[23,89],"of":[24,28,38,51,69,77,111,123,133,201,229,274,277],"the":[25,48,60,64,67,75,78,108,120,164,214,220,272],"execution":[26,49,105,121,244,300],"time":[27,50,106,122,301],"any":[29],"given":[30,188],"application.":[32,221],"For":[33],"example,":[34],"users":[35],"and":[36,74,140,156,251,287],"operators":[37],"a":[39,99,103,169,187,191,259,275,295],"often":[42],"insights":[45],"on":[46,223],"how":[47],"an":[52,174,238],"application":[53,101,189],"likely":[55],"be":[57,81],"impacted":[58],"by":[59],"resources":[61,160],"allocated":[62],"application,":[65],"e.g.,":[66],"number":[68],"executor":[71],"cores":[72],"assigned,":[73],"size":[76],"processed.":[82],"Job":[83],"schedulers":[84],"can":[85,242],"benefit":[86],"from":[87,208],"fast":[88],"at":[90],"runtime":[91],"would":[93],"allow":[94],"them":[95],"quickly":[97],"conFigure":[98],"for":[102,149,163,246],"desired":[104],"using":[107,261],"least":[109],"amount":[110],"resources.":[112],"While":[113],"others":[114],"have":[115],"developed":[116],"models":[117,127],"predict":[119,243,271],"applications,":[125],"such":[126,309],"typically":[128],"extensive":[130],"prior":[131],"executions":[132,211,266],"applications":[134,279],"under":[135,190],"various":[136],"resource":[137,193,248],"allocation":[138,194,249],"settings":[139,250],"sizes.":[142,254],"Consequently,":[143],"these":[144,209,224,263],"techniques":[145],"not":[147],"suited":[148],"situations":[150],"where":[151],"predictions":[153],"required":[155],"very":[157],"little":[158],"available":[162],"experimentation":[165],"needed":[166],"build":[168],"model.":[170],"This":[171],"paper":[172],"proposes":[173],"alternative":[175],"approach":[176,184],"called":[177],"PERIDOT":[178,268],"addresses":[180],"this":[181],"limitation.":[182],"involves":[185],"executing":[186],"fixed":[192],"setting":[195],"with":[196,227,308],"two":[197,210,264],"different-sized,":[198],"small":[199],"subsets":[200],"its":[202],"input":[203,252],"data.":[204,312],"It":[205],"analyzes":[206],"logs":[207],"estimate":[213],"dependencies":[215,225],"between":[216],"internal":[217],"stages":[218],"in":[219],"Information":[222],"combined":[226],"knowledge":[228],"Spark's":[230],"partitioning":[232],"mechanisms":[233],"derive":[237],"analytic":[239],"model":[240,260],"times":[245],"other":[247],"We":[255],"show":[256,293],"deriving":[258],"just":[262],"reference":[265],"allows":[267],"accurately":[270],"performance":[273],"variety":[276],"spanning":[280],"text":[281],"analytics,":[282],"linear":[283],"algebra,":[284],"machine":[285,297],"learning":[286,298],"SQL.":[289],"In":[290],"contrast,":[291],"we":[292],"state-of-the-art":[296],"based":[299],"prediction":[302],"algorithm":[303],"performs":[304],"poorly":[305],"when":[306],"presented":[307],"limited":[310],"training":[311]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}