{"id":"https://openalex.org/W2583728456","doi":"https://doi.org/10.1109/bigdata.2016.7840951","title":"SS-dedup: A high throughput stateful data routing algorithm for cluster deduplication system","display_name":"SS-dedup: A high throughput stateful data routing algorithm for cluster deduplication system","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583728456","doi":"https://doi.org/10.1109/bigdata.2016.7840951","mag":"2583728456"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5025209912","display_name":"Zhihao Huang","orcid":"https://orcid.org/0000-0002-2682-9007"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Huang","raw_affiliation_strings":["Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423804","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-5244-9473"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353805","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-1450-9241"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shcnzhen Key Lab of Info. Theory & Future Network Architecture, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101588659","display_name":"Wei He","orcid":"https://orcid.org/0009-0002-9240-5330"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei He","raw_affiliation_strings":["Guangdong Super Computing & Data Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Super Computing & Data Technology Co., Ltd","institution_ids":["https://openalex.org/I4210144487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5909,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75445771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2991","last_page":"2995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","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/T11478","display_name":"Caching and Content Delivery","score":0.9980000257492065,"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/data-deduplication","display_name":"Data deduplication","score":0.9470983743667603},{"id":"https://openalex.org/keywords/stateful-firewall","display_name":"Stateful firewall","score":0.8779671788215637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8119357824325562},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7537736892700195},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5388941168785095},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4631373882293701},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4423779547214508},{"id":"https://openalex.org/keywords/file-server","display_name":"File server","score":0.42825815081596375},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42712298035621643},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.418023943901062},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34765931963920593},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27165210247039795}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9470983743667603},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.8779671788215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119357824325562},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7537736892700195},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5388941168785095},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4631373882293701},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4423779547214508},{"id":"https://openalex.org/C4373008","wikidata":"https://www.wikidata.org/wiki/Q513349","display_name":"File server","level":2,"score":0.42825815081596375},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42712298035621643},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.418023943901062},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34765931963920593},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27165210247039795},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W24740120","https://openalex.org/W26020480","https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1576397915","https://openalex.org/W1969126835","https://openalex.org/W2055899630","https://openalex.org/W2081193615","https://openalex.org/W2119565742","https://openalex.org/W2119738171","https://openalex.org/W2169353679","https://openalex.org/W2345185127","https://openalex.org/W4243055721","https://openalex.org/W6600228218","https://openalex.org/W6601033703","https://openalex.org/W6601060166","https://openalex.org/W6608138927","https://openalex.org/W6634463810"],"related_works":["https://openalex.org/W2799329589","https://openalex.org/W2535099400","https://openalex.org/W2094337296","https://openalex.org/W2165440220","https://openalex.org/W4289655417","https://openalex.org/W2399644275","https://openalex.org/W2560958726","https://openalex.org/W3204477168","https://openalex.org/W1735858552","https://openalex.org/W2005966532"],"abstract_inverted_index":{"As":[0,23],"data":[1,5,27,56,91,126],"grows":[2],"exponentially":[3],"within":[4],"centers,":[6],"cluster":[7,43,60],"deduplication":[8,18,36,44,61,78,99,140],"storage":[9,45,62],"systems":[10],"face":[11],"challenges":[12],"in":[13,42,84,114],"providing":[14],"high":[15,17,139],"throughput,":[16],"ratio":[19,79,100],"and":[20,39,70,81,107,138,149],"load":[21,40,72,136],"balance.":[22],"the":[24,35,75],"key":[25],"technique,":[26],"routing":[28,57],"algorithm":[29,58],"has":[30],"a":[31,53],"strong":[32],"impact":[33],"on":[34],"ratio,":[37,141],"throughput":[38,69,96],"balance":[41,73,137],"systems.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"SS-Dedup,":[52],"novel":[54],"stateful":[55],"for":[59,124],"system":[63,68,95,152],"which":[64],"can":[65],"achieve":[66],"higher":[67,151],"good":[71,135],"at":[74],"cost":[76],"of":[77,90,120],"loss":[80],"memory":[82],"space":[83],"client":[85,115],"servers.":[86],"SS-Dedup":[87,110,142],"takes":[88,143],"advantage":[89],"similarity":[92],"to":[93,103,117],"increases":[94],"with":[97],"little":[98],"loss.":[101],"Specifically,":[102],"decrease":[104],"network":[105,147],"traffic":[106],"response":[108],"time,":[109],"maintains":[111],"LRU":[112],"caches":[113],"servers":[116],"store":[118],"fingerprints":[119],"historical":[121],"routed":[122],"chunks":[123],"each":[125],"server.":[127],"Our":[128],"experiment":[129],"results":[130],"show":[131],"that":[132],"while":[133],"maintaining":[134],"up":[144],"much":[145],"lower":[146],"bandwidth":[148],"provides":[150],"throughput.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}