{"id":"https://openalex.org/W2145007880","doi":"https://doi.org/10.1109/ccgrid.2012.56","title":"Optimizing Completion Time and Resource Provisioning of Pig Programs","display_name":"Optimizing Completion Time and Resource Provisioning of Pig Programs","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2145007880","doi":"https://doi.org/10.1109/ccgrid.2012.56","mag":"2145007880"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid.2012.56","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2012.56","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)","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/A5011774662","display_name":"Zhuoyao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoyao Zhang","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA","University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016669578","display_name":"Ludmila Cherkasova","orcid":"https://orcid.org/0000-0002-9333-4901"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludmila Cherkasova","raw_affiliation_strings":["Hewlett Packard Laboratory, Palo Alto, CA, USA","Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090056582","display_name":"Abhishek Verma","orcid":"https://orcid.org/0000-0002-0491-178X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Verma","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090052860","display_name":"Boon Thau Loo","orcid":"https://orcid.org/0000-0002-4757-1746"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boon Thau Loo","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA","University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1445,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95519439,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"811","last_page":"816"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9850999712944031,"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":0.8789753317832947},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.5244984030723572},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5213919281959534},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.5073582530021667},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5057361125946045},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.48267415165901184},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.45217210054397583},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4398632049560547},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43232178688049316},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4183367192745209},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3394618630409241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789753317832947},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.5244984030723572},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5213919281959534},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.5073582530021667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5057361125946045},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.48267415165901184},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.45217210054397583},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4398632049560547},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43232178688049316},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4183367192745209},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3394618630409241},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ccgrid.2012.56","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2012.56","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.250.8845","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.250.8845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/%7Ezhuoyao/Zhuoyao_Homepage/paper/CCOPT12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.9777","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.9777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Lucy_Cherkasova/papers/Pig-CCOPT.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5799999833106995,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1508832460","https://openalex.org/W1834532152","https://openalex.org/W2002472616","https://openalex.org/W2024085737","https://openalex.org/W2100830825","https://openalex.org/W2110086534","https://openalex.org/W2112013978","https://openalex.org/W2119208045","https://openalex.org/W2119400430","https://openalex.org/W2123537546","https://openalex.org/W2142031898","https://openalex.org/W2173213060","https://openalex.org/W4246315676","https://openalex.org/W6630471841","https://openalex.org/W6639007902"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W2893779165","https://openalex.org/W1480123525","https://openalex.org/W2620865396"],"abstract_inverted_index":{"As":[0],"cloud":[1],"computing":[2],"continues":[3],"to":[4,75,193],"mature,":[5],"IT":[6],"managers":[7],"have":[8,74],"started":[9],"concentrating":[10],"on":[11,45,178],"the":[12,35,99,114,149,174,203],"support":[13],"of":[14,19,47,67,102,109,116,120,152,225,231],"additional":[15],"performance":[16,28,86,185],"requirements:":[17],"quality":[18],"service":[20,27],"and":[21,122,167,222],"tailored":[22],"resource":[23,195],"allocation":[24],"for":[25,50,89,126,187],"achieving":[26],"goals.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,140,181],"consider":[34],"popular":[36],"Pig":[37,90,104,129,144,188],"framework":[38,88],"that":[39,92],"provides":[40],"a":[41,79,85,103,107,128,132,143,159,212,223,229],"high-level":[42],"SQL-like":[43],"abstraction":[44],"top":[46],"MapReduce":[48,68],"engine":[49],"processing":[51,72],"large":[52],"data":[53,71],"sets.":[54],"Programs":[55],"written":[56],"in":[57,164,173,198,211],"such":[58],"frameworks":[59],"are":[60],"compiled":[61],"into":[62],"directed":[63],"acyclic":[64],"graphs":[65],"(DAGs)":[66],"jobs.":[69,155],"Often,":[70],"applications":[73],"produce":[76],"results":[77],"by":[78,147],"certain":[80],"time":[81,101,162],"deadline.":[82,135],"We":[83,207],"design":[84],"modeling":[87],"programs":[91],"solves":[93],"two":[94,217],"inter-related":[95],"problems:":[96],"(i)":[97],"estimating":[98,113],"completion":[100,161],"program":[105,130,145,160],"as":[106],"function":[108],"allocated":[110],"resources,":[111],"(ii)":[112],"amount":[115],"resources":[117],"(a":[118],"number":[119],"map":[121],"reduce":[123],"slots)":[124],"required":[125],"completing":[127],"with":[131,202],"given":[133],"(soft)":[134],"To":[136],"achieve":[137],"these":[138],"goals,":[139],"first,":[141],"optimize":[142],"execution":[146],"enforcing":[148],"optimal":[150],"schedule":[151],"its":[153],"concurrent":[154],"This":[156,190],"optimization":[157],"reduces":[158],"(10%-27%":[163],"our":[165,179,199,209],"experiments),":[166],"moreover,":[168],"it":[169],"eliminates":[170],"possible":[171],"non-determinism":[172],"DAGs":[175],"execution.":[176],"Based":[177],"optimization,":[180],"propose":[182],"an":[183],"accurate":[184],"model":[186],"programs.":[189],"approach":[191,210],"leads":[192],"significant":[194],"savings":[196],"(20%-60%":[197],"experiments)":[200],"compared":[201],"original,":[204],"unoptimized":[205],"solution.":[206],"validate":[208],"66-node":[213],"Hadoop":[214],"cluster":[215],"using":[216],"workload":[218],"sets:":[219],"TPC-H":[220],"queries":[221,227],"set":[224],"customized":[226],"mining":[228],"collection":[230],"HP":[232],"Labs'":[233],"web":[234],"proxy":[235],"logs.":[236]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
