{"id":"https://openalex.org/W3010780701","doi":"https://doi.org/10.1109/pdcat46702.2019.00046","title":"A Holistic Stream Partitioning Algorithm for Distributed Stream Processing Systems","display_name":"A Holistic Stream Partitioning Algorithm for Distributed Stream Processing Systems","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010780701","doi":"https://doi.org/10.1109/pdcat46702.2019.00046","mag":"3010780701"},"language":"en","primary_location":{"id":"doi:10.1109/pdcat46702.2019.00046","doi":"https://doi.org/10.1109/pdcat46702.2019.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdcat46702.2019.00046","pdf_url":null,"source":{"id":"https://openalex.org/S7407088834","display_name":"International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5069767883","display_name":"Kejian Li","orcid":"https://orcid.org/0009-0005-8120-771X","observed_orcids":["https://orcid.org/0009-0005-8120-771X"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4405272608","display_name":"Key Laboratory of Popular Type of High-performance Computer of Guangdong Province","ror":"https://ror.org/04e505q76","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405272608"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejian Li","raw_affiliation_strings":["Shenzhen University","Guangdong Province Key Laboratory of Popular High Performance Computers, Guangdong Province Engineering Center of China-made High Performance Data Computing System, College of Computer Science and Software Engineering Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Guangdong Province Key Laboratory of Popular High Performance Computers, Guangdong Province Engineering Center of China-made High Performance Data Computing System, College of Computer Science and Software Engineering Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4405272608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913215","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-0946-7075","observed_orcids":["https://orcid.org/0000-0002-0946-7075"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4405272608","display_name":"Key Laboratory of Popular Type of High-performance Computer of Guangdong Province","ror":"https://ror.org/04e505q76","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405272608"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["Shenzhen University","Guangdong Province Key Laboratory of Popular High Performance Computers, Guangdong Province Engineering Center of China-made High Performance Data Computing System, College of Computer Science and Software Engineering Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Guangdong Province Key Laboratory of Popular High Performance Computers, Guangdong Province Engineering Center of China-made High Performance Data Computing System, College of Computer Science and Software Engineering Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4405272608"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070665912","display_name":"Minhua Lu","orcid":"https://orcid.org/0000-0002-7050-5579","observed_orcids":["https://orcid.org/0000-0002-7050-5579"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minhua Lu","raw_affiliation_strings":["Shenzhen University","School of biomedical engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of biomedical engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"2019","issue":null,"first_page":"202","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0003000000142492354,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.00019999999494757503,"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/distributed-stream-processing","display_name":"distributed stream processing","score":0.9739999771118164},{"id":"https://openalex.org/keywords/key-splitting","display_name":"key splitting","score":0.7850000262260437},{"id":"https://openalex.org/keywords/load-balancing","display_name":"load balancing","score":0.7770000100135803},{"id":"https://openalex.org/keywords/replication-factor","display_name":"replication factor","score":0.8370000123977661},{"id":"https://openalex.org/keywords/heavy-hitters","display_name":"heavy hitters","score":0.7739999890327454},{"id":"https://openalex.org/keywords/hash-partitioning","display_name":"hash partitioning","score":0.8119999766349792},{"id":"https://openalex.org/keywords/stateful-applications","display_name":"stateful applications","score":0.6809999942779541},{"id":"https://openalex.org/keywords/memory-usage","display_name":"memory usage","score":0.5360000133514404},{"id":"https://openalex.org/keywords/routing-table-size","display_name":"routing table size","score":0.5260000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596794605255127},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6792374849319458},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6607807874679565},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.6317398548126221},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6068445444107056},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.5247961282730103},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4827794134616852},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44875818490982056},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44006314873695374},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43242591619491577},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4218834936618805},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.35471397638320923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2829892933368683},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2703434228897095},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pdcat46702.2019.00046","doi":"https://doi.org/10.1109/pdcat46702.2019.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdcat46702.2019.00046","pdf_url":null,"source":{"id":"https://openalex.org/S7407088834","display_name":"International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","raw_type":"proceedings-article"},{"id":"mag:3041061482","doi":null,"is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002253036080104","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5378999710083008}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W139562302","https://openalex.org/W1553409264","https://openalex.org/W1976821017","https://openalex.org/W1982092405","https://openalex.org/W2023478510","https://openalex.org/W2060540987","https://openalex.org/W2069980026","https://openalex.org/W2117702591","https://openalex.org/W2124945926","https://openalex.org/W2128362607","https://openalex.org/W2144982963","https://openalex.org/W2148222209","https://openalex.org/W2223348197","https://openalex.org/W2536427613","https://openalex.org/W2549484849","https://openalex.org/W2566979091","https://openalex.org/W2750816680","https://openalex.org/W2803123410"],"related_works":["https://openalex.org/W2803123410","https://openalex.org/W2601029549","https://openalex.org/W7165892519","https://openalex.org/W2124945926","https://openalex.org/W2223348197","https://openalex.org/W2232640716","https://openalex.org/W3087674339","https://openalex.org/W2768459599","https://openalex.org/W2536427613","https://openalex.org/W4416173435"],"abstract_inverted_index":{"The":[0],"performances":[1],"of":[2,14,61,72,92,98,139,157,189,218,228],"modern":[3],"distributed":[4],"stream":[5,105,230],"processing":[6,106,124],"systems":[7,107],"are":[8,25],"critically":[9],"affected":[10],"by":[11],"the":[12,15,64,70,96,134,137,140,150,172,178,187,190,194,212],"distribution":[13,141],"load":[16,62,121,159,219],"across":[17],"workers.":[18],"Skewed":[19],"data":[20],"streams":[21],"in":[22,63,104,143,216],"real":[23],"world":[24],"very":[26],"common":[27],"and":[28,76,108,123,136,223],"pose":[29],"a":[30,44,54,89,110],"great":[31,55],"challenge":[32],"to":[33,47,50,57,94,113,128,145,161,165,185,211],"these":[34],"systems,":[35],"especially":[36],"for":[37,101,171,193],"stateful":[38],"applications.":[39],"Key":[40],"splitting,":[41],"which":[42],"allows":[43],"single":[45],"key":[46,99],"be":[48],"routed":[49],"multiple":[51],"workers,":[52],"is":[53],"idea":[56],"achieve":[58],"good":[59],"balance":[60],"cluster.":[65],"However,":[66],"it":[67,152,180],"comes":[68],"with":[69],"cost":[71,97],"increased":[73],"memory":[74,147],"consumption":[75],"computation":[77],"overhead":[78],"as":[79,81,196,198],"well":[80],"network":[82],"communication.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"present":[88],"new":[90],"definition":[91],"metric":[93],"model":[95],"splitting":[100],"intra-operator":[102],"parallelism":[103],"provide":[109],"novel":[111],"perspective":[112],"reduce":[114,146],"replication":[115,221],"factor":[116,222],"while":[117],"keeping":[118],"both":[119],"overall":[120],"imbalance":[122,160],"latency":[125,224],"low.":[126],"Similar":[127],"previous":[129],"work,":[130],"our":[131,154,205],"approach":[132,206],"treats":[133],"head":[135,195],"tail":[138],"differently":[142],"order":[144],"requirements.":[148],"For":[149,177],"head,":[151],"uses":[153,182],"proposed":[155],"notion":[156],"regional":[158],"decide":[162],"dynamically":[163],"whether":[164],"make":[166],"one":[167],"more":[168],"worker":[169],"responsible":[170],"heavy":[173],"hitter":[174],"or":[175],"not.":[176],"tail,":[179],"simply":[181],"hash":[183],"partitioning":[184,214],"keep":[186],"size":[188],"routing":[191],"table":[192],"small":[197],"possible.":[199],"Extensive":[200],"experimental":[201],"evaluation":[202],"demonstrates":[203],"that":[204],"provides":[207],"superior":[208],"performance":[209],"compared":[210],"state-of-the-art":[213],"algorithms":[215],"terms":[217],"imbalance,":[220],"over":[225],"different":[226],"levels":[227],"skewed":[229],"distributions.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-03-23T00:00:00"}