{"id":"https://openalex.org/W2773227638","doi":"https://doi.org/10.1145/3148055.3148068","title":"Characterization of Big Data Stream Processing Pipeline","display_name":"Characterization of Big Data Stream Processing Pipeline","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2773227638","doi":"https://doi.org/10.1145/3148055.3148068","mag":"2773227638"},"language":"en","primary_location":{"id":"doi:10.1145/3148055.3148068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148055.3148068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies","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/A5102836528","display_name":"M. Haseeb Javed","orcid":"https://orcid.org/0000-0002-2812-1045"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Haseeb Javed","raw_affiliation_strings":["Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067748041","display_name":"Xiaoyi Lu","orcid":"https://orcid.org/0000-0001-7581-8905"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Lu","raw_affiliation_strings":["Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. (DK) Panda","raw_affiliation_strings":["Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102836528"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.9017,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92993316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.996999979019165,"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":0.8282362222671509},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7683599591255188},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.7360587120056152},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7310473322868347},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.5863667130470276},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4605070948600769},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.44093823432922363},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42703312635421753},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.41559261083602905},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36058667302131653},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.32230764627456665},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23597970604896545},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16113978624343872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09308838844299316},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08748537302017212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282362222671509},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7683599591255188},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.7360587120056152},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7310473322868347},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.5863667130470276},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4605070948600769},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.44093823432922363},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42703312635421753},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.41559261083602905},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36058667302131653},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32230764627456665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23597970604896545},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16113978624343872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09308838844299316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08748537302017212}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3148055.3148068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148055.3148068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G2798451465","display_name":null,"funder_award_id":"CNS-1419123","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W192446467","https://openalex.org/W782787506","https://openalex.org/W1635892993","https://openalex.org/W1831560769","https://openalex.org/W1968781019","https://openalex.org/W1976821017","https://openalex.org/W2003272624","https://openalex.org/W2008503861","https://openalex.org/W2071704971","https://openalex.org/W2072627547","https://openalex.org/W2110946051","https://openalex.org/W2115503987","https://openalex.org/W2119738171","https://openalex.org/W2119745055","https://openalex.org/W2126969367","https://openalex.org/W2131053137","https://openalex.org/W2131975293","https://openalex.org/W2149576945","https://openalex.org/W2153972927","https://openalex.org/W2244876453","https://openalex.org/W2247317079","https://openalex.org/W2311891150","https://openalex.org/W2401112755","https://openalex.org/W2419660933","https://openalex.org/W2486439025","https://openalex.org/W2498111289","https://openalex.org/W2546551642","https://openalex.org/W2566979091","https://openalex.org/W2576742135","https://openalex.org/W2578361720"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W2886490431","https://openalex.org/W4361801939","https://openalex.org/W4317418912","https://openalex.org/W2360131081","https://openalex.org/W180351855"],"abstract_inverted_index":{"In":[0],"recent":[1],"years":[2],"there":[3],"has":[4,200],"been":[5],"a":[6,34,42,100,131,176,187,263],"surge":[7],"in":[8,17,221,237],"applications":[9,52],"focusing":[10],"on":[11,85,203],"streaming":[12,134,153,178,209,223],"data":[13,133,198],"to":[14,27,55,71,92,95,107,113,173,184,249,261,266],"generate":[15],"insights":[16],"real-time.":[18],"Both":[19],"academia,":[20],"as":[21,23,139,145],"well":[22],"industry,":[24],"have":[25,53,83],"tried":[26],"address":[28,123],"this":[29,124],"use":[30,57],"case":[31],"by":[32,119],"developing":[33],"variety":[35],"of":[36,58,81,99,110,130,196,207,234,257,270],"Stream":[37],"Processing":[38],"Engines":[39],"(SPEs)":[40],"with":[41],"diverse":[43],"feature":[44],"set.":[45],"On":[46],"the":[47,79,116,128,140,146,152,194,204,208,222,254,258,267,271],"other":[48],"hand,":[49],"Big":[50,73],"Data":[51,74],"started":[54],"make":[56],"High-Performance":[59],"Computing":[60],"(HPC)":[61],"which":[62],"possess":[63],"superior":[64],"memory,":[65],"I/O,":[66],"and":[67,104,142,159,169,211,225],"networking":[68],"resources":[69,117],"compared":[70],"typical":[72,177],"clusters.":[75,87,121],"Recent":[76],"studies":[77,90],"evaluating":[78],"performance":[80,129],"SPEs":[82],"focused":[84],"commodity":[86],"However,":[88],"exhaustive":[89],"need":[91],"be":[93,262],"performed":[94],"profile":[96,127],"individual":[97],"stages":[98,112,220,256],"stream":[101,199,243,259],"processing":[102],"pipeline":[103,135,154,224,260],"how":[105,214],"best":[106,114],"optimize":[108],"each":[109],"these":[111],"leverage":[115],"provided":[118],"HPC":[120],"To":[122],"issue,":[125],"we":[126,191,252],"big":[132],"using":[136],"Apache":[137,143],"Flink":[138],"SPE":[141],"Kafka":[144],"intermediate":[147,255],"message":[148],"queue.":[149],"We":[150],"break":[151],"into":[155],"two":[156,164],"distinct":[157],"phases":[158],"evaluate":[160],"percentile":[161,239],"latencies":[162],"for":[163,218],"different":[165,219,226],"networks,":[166],"namely":[167],"40GbE":[168],"InfiniBand":[170],"EDR":[171],"(100Gbps),":[172],"determine":[174],"if":[175,212],"application":[179],"is":[180,245],"network":[181,227],"intensive":[182],"enough":[183],"benefit":[185],"from":[186,247],"faster":[188],"interconnect.":[189],"Moreover,":[190,251],"explore":[192],"whether":[193],"volume":[195,244],"input":[197,242],"any":[201],"effect":[202],"latency":[205,240,269],"characteristics":[206],"pipeline,":[210],"so":[213],"does":[215],"it":[216],"compare":[217],"interconnects.":[228],"Our":[229],"experiments":[230],"show":[231],"an":[232],"increase":[233],"over":[235],"10x":[236],"98":[238],"when":[241],"increased":[246],"128MB/s":[248],"256MB/s.":[250],"find":[253],"significant":[264],"contributor":[265],"overall":[268],"system.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}