{"id":"https://openalex.org/W2735413012","doi":"https://doi.org/10.1109/icdcs.2017.131","title":"Optimizing Shuffle in Wide-Area Data Analytics","display_name":"Optimizing Shuffle in Wide-Area Data Analytics","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2735413012","doi":"https://doi.org/10.1109/icdcs.2017.131","mag":"2735413012"},"language":"en","primary_location":{"id":"doi:10.1109/icdcs.2017.131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2017.131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)","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/A5100759864","display_name":"Shuhao Liu","orcid":"https://orcid.org/0000-0002-4892-0979"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shuhao Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446064","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9301-5989"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083596391","display_name":"Baochun Li","orcid":"https://orcid.org/0000-0003-2404-0974"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Baochun Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"560","last_page":"571"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9987000226974487,"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/T12127","display_name":"Software System Performance and Reliability","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":0.8441177010536194},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7554717659950256},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5777906179428101},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5627369284629822},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5106809735298157},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4671477675437927},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.44073885679244995},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4185038208961487},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4102877974510193},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3866284489631653},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.35639506578445435},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3243125081062317},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24711042642593384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441177010536194},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7554717659950256},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5777906179428101},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5627369284629822},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5106809735298157},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4671477675437927},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.44073885679244995},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4185038208961487},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4102877974510193},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3866284489631653},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.35639506578445435},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3243125081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24711042642593384},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdcs.2017.131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2017.131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1230574503","https://openalex.org/W1249613807","https://openalex.org/W1969299781","https://openalex.org/W1986566751","https://openalex.org/W2005380621","https://openalex.org/W2035309843","https://openalex.org/W2122370965","https://openalex.org/W2155072926","https://openalex.org/W2267569004","https://openalex.org/W2295862636","https://openalex.org/W2329835557","https://openalex.org/W2465838301","https://openalex.org/W2482213519","https://openalex.org/W2496080211","https://openalex.org/W2562897376","https://openalex.org/W2912802084","https://openalex.org/W6628075071","https://openalex.org/W6628088091","https://openalex.org/W6646871274","https://openalex.org/W6682930621","https://openalex.org/W6697552392","https://openalex.org/W6702204512","https://openalex.org/W6731119795","https://openalex.org/W6758383543"],"related_works":["https://openalex.org/W3191926225","https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W2980555063","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W4382315681","https://openalex.org/W2794907032","https://openalex.org/W4255802207"],"abstract_inverted_index":{"As":[0,56],"increasingly":[1],"large":[2],"volumes":[3],"of":[4,112,118,130,136,154,167],"raw":[5],"data":[6,20,35,81,93,113,129,161],"are":[7,42,54],"generated":[8],"at":[9],"geographically":[10],"distributed":[11],"datacenters,":[12,138],"they":[13],"need":[14,70],"to":[15,45,122,133,142,190,197,201],"be":[16,63],"efficiently":[17],"processed":[18],"by":[19,158,195],"analytic":[21,52,114,156],"jobs":[22,53,157],"spanning":[23],"multiple":[24],"datacenters":[25,60],"across":[26,148,177],"wide-area":[27,51,57,80,155],"networks.":[28],"Designed":[29],"for":[30,71,79],"a":[31,68,72,90,101,134,140],"single":[32],"datacenter,":[33],"existing":[34,203],"processing":[36],"frameworks,":[37],"such":[38],"as":[39,139,199],"Apache":[40,98],"Spark,":[41,99],"not":[43,62],"able":[44,189],"deliver":[46],"satisfactory":[47],"performance":[48,153],"when":[49],"these":[50],"executed.":[55],"networks":[58],"interconnecting":[59],"may":[61],"congestion":[64],"free,":[65],"there":[66],"is":[67,77,121,188],"compelling":[69],"new":[73,91],"system":[74],"framework":[75,95,120,187],"that":[76,184],"optimized":[78],"analytics.":[82],"In":[83],"this":[84,119],"paper,":[85],"we":[86],"design":[87],"and":[88,124],"implement":[89],"proactive":[92],"aggregation":[94],"based":[96],"on":[97,103],"with":[100],"focus":[102],"optimizing":[104],"the":[105,127,152,165,202],"network":[106],"traffic":[107],"incurred":[108],"in":[109,206],"shuffle":[110],"stages":[111],"jobs.":[115],"The":[116],"objective":[117],"strategically":[123],"proactively":[125],"aggregate":[126],"output":[128],"mapper":[131],"tasks":[132],"subset":[135],"worker":[137],"replacement":[141],"Spark's":[143],"original":[144],"passive":[145],"fetch":[146],"mechanism":[147],"datacenters.":[149],"It":[150],"improves":[151,164],"avoiding":[159],"repetitive":[160],"transfers,":[162],"which":[163],"utilization":[166],"inter-datacenter":[168],"links.":[169],"Our":[170],"extensive":[171],"experimental":[172],"results":[173],"using":[174],"standard":[175],"benchmarks":[176],"six":[178],"Amazon":[179],"EC2":[180],"regions":[181],"have":[182],"shown":[183],"our":[185],"proposed":[186],"reduce":[191],"job":[192],"completion":[193],"times":[194],"up":[196],"73%,":[198],"compared":[200],"baseline":[204],"implementation":[205],"Spark.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}