{"id":"https://openalex.org/W2124945926","doi":"https://doi.org/10.1109/icde.2015.7113279","title":"The power of both choices: Practical load balancing for distributed stream processing engines","display_name":"The power of both choices: Practical load balancing for distributed stream processing engines","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2124945926","doi":"https://doi.org/10.1109/icde.2015.7113279","mag":"2124945926"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2015.7113279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1504.00788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Muhammad Anis Uddin Nasir","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Muhammad Anis Uddin Nasir","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gianmarco De Francisci Morales","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gianmarco De Francisci Morales","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"David Garcia-Soriano","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Garcia-Soriano","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nicolas Kourtellis","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nicolas Kourtellis","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Serafini","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Marco Serafini","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":15.4506,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99098488,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.7429999709129333},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7103000283241272},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.6072999835014343},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/load-management","display_name":"Load management","score":0.5273000001907349},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45410001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767000198364258},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.7429999709129333},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7103000283241272},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6664999723434448},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C2779370713","wikidata":"https://www.wikidata.org/wiki/Q357554","display_name":"Load management","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45410001277923584},{"id":"https://openalex.org/C2779777743","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Load Shedding","level":4,"score":0.3926999866962433},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C36877392","wikidata":"https://www.wikidata.org/wiki/Q1229571","display_name":"Distributed power","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C102359118","wikidata":"https://www.wikidata.org/wiki/Q178163","display_name":"Round-robin DNS","level":4,"score":0.26499998569488525},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C161597957","wikidata":"https://www.wikidata.org/wiki/Q16251507","display_name":"Network Load Balancing Services","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2015.7113279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1504.00788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.00788","pdf_url":"https://arxiv.org/pdf/1504.00788","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1504.00788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.00788","pdf_url":"https://arxiv.org/pdf/1504.00788","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1678178911","https://openalex.org/W1969970763","https://openalex.org/W1980744864","https://openalex.org/W2017185378","https://openalex.org/W2020765652","https://openalex.org/W2021124283","https://openalex.org/W2029709107","https://openalex.org/W2030903277","https://openalex.org/W2035543557","https://openalex.org/W2056012370","https://openalex.org/W2064635301","https://openalex.org/W2069817080","https://openalex.org/W2091323212","https://openalex.org/W2102849319","https://openalex.org/W2117410972","https://openalex.org/W2117702591","https://openalex.org/W2119745055","https://openalex.org/W2125775320","https://openalex.org/W2140509629","https://openalex.org/W2140955554","https://openalex.org/W2152558130","https://openalex.org/W2152837238","https://openalex.org/W2154894831","https://openalex.org/W2162747054","https://openalex.org/W2912437396","https://openalex.org/W4250390143","https://openalex.org/W6633322224","https://openalex.org/W6636450965","https://openalex.org/W6656532703","https://openalex.org/W6684418397"],"related_works":[],"abstract_inverted_index":{"We":[0,20,73],"study":[1],"the":[2,16,33,90],"problem":[3],"of":[4,18,36,98,112],"load":[5,53,61,91,104],"balancing":[6,62],"in":[7,15,116,122],"distributed":[8,41],"stream":[9,28],"processing":[10],"engines,":[11],"which":[12],"is":[13],"exacerbated":[14],"presence":[17],"skew.":[19],"introduce":[21],"Partial":[22],"Key":[23],"Grouping":[24],"(PKG),":[25],"a":[26,40,127],"new":[27],"partitioning":[29],"scheme":[30],"that":[31],"adapts":[32],"classical":[34],"\u201cpower":[35],"two":[37,46],"choices\u201d":[38],"to":[39,85,95,114,120],"streaming":[42],"setting":[43],"by":[44,93],"leveraging":[45],"novel":[47],"techniques:":[48],"key":[49,64],"splitting":[50],"and":[51,82,100,118],"local":[52],"estimation.":[54],"In":[55],"so":[56],"doing,":[57],"it":[58],"achieves":[59,102],"better":[60],"than":[63,70],"grouping":[65],"while":[66],"being":[67],"more":[68],"scalable":[69],"shuffle":[71],"grouping.":[72],"test":[74],"PKG":[75,88],"on":[76,126],"several":[77,96],"large":[78],"datasets,":[79],"both":[80],"real-world":[81],"synthetic.":[83],"Compared":[84],"standard":[86],"hashing,":[87],"reduces":[89],"imbalance":[92],"up":[94,113,119],"orders":[97],"magnitude,":[99],"often":[101],"nearly-perfect":[103],"balance.":[105],"This":[106],"result":[107],"translates":[108],"into":[109],"an":[110],"improvement":[111],"60%":[115],"throughput":[117],"45%":[121],"latency":[123],"when":[124],"deployed":[125],"real":[128],"Storm":[129],"cluster.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}