{"id":"https://openalex.org/W2073370301","doi":"https://doi.org/10.1145/2385603.2385606","title":"WAN-optimized replication of backup datasets using stream-informed delta compression","display_name":"WAN-optimized replication of backup datasets using stream-informed delta compression","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2073370301","doi":"https://doi.org/10.1145/2385603.2385606","mag":"2073370301"},"language":"en","primary_location":{"id":"doi:10.1145/2385603.2385606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2385603.2385606","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-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":null,"display_name":"Phlip Shilane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phlip Shilane","raw_affiliation_strings":["Backup Recovery Systems Division, EMC Corporation","Backup Recovery Systems Division, EMC Corporation#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation","institution_ids":[]},{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111884330","display_name":"Mark Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Huang","raw_affiliation_strings":["Backup Recovery Systems Division, EMC Corporation","Backup Recovery Systems Division, EMC Corporation#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation","institution_ids":[]},{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103954420","display_name":"Grant Wallace","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant Wallace","raw_affiliation_strings":["Backup Recovery Systems Division, EMC Corporation","Backup Recovery Systems Division, EMC Corporation#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation","institution_ids":[]},{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112516579","display_name":"Windsor Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Windsor Hsu","raw_affiliation_strings":["Backup Recovery Systems Division, EMC Corporation","Backup Recovery Systems Division, EMC Corporation#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation","institution_ids":[]},{"raw_affiliation_string":"Backup Recovery Systems Division, EMC Corporation#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4527,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.97405839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11478","display_name":"Caching and Content Delivery","score":0.9987999796867371,"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/T11896","display_name":"Opportunistic and Delay-Tolerant Networks","score":0.9952999949455261,"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/backup","display_name":"Backup","score":0.8957529067993164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8797492980957031},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8123913407325745},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6267046332359314},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5127840638160706},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.47822993993759155},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4402509331703186},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4383942186832428},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38371169567108154},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35456162691116333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35424476861953735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09977087378501892},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08818197250366211}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8957529067993164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8797492980957031},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8123913407325745},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6267046332359314},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5127840638160706},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.47822993993759155},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4402509331703186},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4383942186832428},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38371169567108154},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35456162691116333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35424476861953735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09977087378501892},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08818197250366211},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2385603.2385606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2385603.2385606","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.1866","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.1866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.princeton.edu/courses/archive/spring13/cos598C/shilane.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W69510097","https://openalex.org/W89823361","https://openalex.org/W96989745","https://openalex.org/W125480971","https://openalex.org/W152583591","https://openalex.org/W162607394","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1508926177","https://openalex.org/W1521407587","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1741747329","https://openalex.org/W1826022669","https://openalex.org/W1947728686","https://openalex.org/W1969126835","https://openalex.org/W1991800036","https://openalex.org/W1993865637","https://openalex.org/W1998817683","https://openalex.org/W2004286258","https://openalex.org/W2007842132","https://openalex.org/W2029673812","https://openalex.org/W2050140640","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2097580253","https://openalex.org/W2099676315","https://openalex.org/W2107551255","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2137092019","https://openalex.org/W2137847645","https://openalex.org/W2138061848","https://openalex.org/W2141378275","https://openalex.org/W2148885851","https://openalex.org/W2164215197","https://openalex.org/W2281363974","https://openalex.org/W2583349018","https://openalex.org/W2912574597","https://openalex.org/W2914831260","https://openalex.org/W4233161060","https://openalex.org/W4243255773","https://openalex.org/W4243382396"],"related_works":["https://openalex.org/W2955195711","https://openalex.org/W3144870715","https://openalex.org/W4285245558","https://openalex.org/W1437397736","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W2348132657"],"abstract_inverted_index":{"Replicating":[0,22],"data":[1,143,188],"off":[2],"site":[3],"is":[4,17,29,48,88,101],"critical":[5],"for":[6,61,118],"disaster":[7],"recovery":[8],"reasons,":[9],"but":[10,33,77],"the":[11,116,152],"current":[12],"approach":[13,137],"of":[14,74,82,93,158,164],"transferring":[15],"tapes":[16],"cumbersome":[18],"and":[19,114,160,180],"error":[20],"prone.":[21],"across":[23,65,141],"a":[24,30,58,66,91,127,133,146,155],"wide":[25],"area":[26],"network":[27,35],"(WAN)":[28],"promising":[31],"alternative,":[32],"fast":[34],"connections":[36],"are":[37],"expensive":[38],"or":[39,130],"impractical":[40],"in":[41,151],"many":[42],"remote":[43],"locations,":[44],"so":[45],"improved":[46],"compression":[47,108,140,174,177],"needed":[49],"to":[50,109,145,186,193],"make":[51],"WAN":[52,67],"replication":[53],"truly":[54],"practical.":[55],"We":[56],"present":[57],"new":[59],"technique":[60],"replicating":[62],"backup":[63,197],"datasets":[64,159],"that":[68,104,131,189],"not":[69],"only":[70],"eliminates":[71,115],"duplicate":[72],"regions":[73,81],"files":[75,83],"(deduplication)":[76],"also":[78],"compresses":[79],"similar":[80],"with":[84],"delta":[85,107,139,176],"compression,":[86,182],"which":[87,183],"available":[89],"as":[90],"feature":[92],"EMC":[94],"Data":[95],"Domain":[96],"systems.":[97],"Our":[98],"main":[99],"contribution":[100],"an":[102,171],"architecture":[103],"adds":[105],"stream-informed":[106],"already":[110],"existing":[111],"deduplication":[112,179],"systems":[113],"need":[117],"new,":[119],"persistent":[120],"indexes.":[121],"Unlike":[122],"techniques":[123],"based":[124],"on":[125],"knowing":[126],"file's":[128],"version":[129],"use":[132],"memory":[134],"cache,":[135],"our":[136,167],"achieves":[138],"all":[142],"replicated":[144],"server":[147],"at":[148],"any":[149],"time":[150],"past.":[153],"From":[154],"detailed":[156],"analysis":[157],"statistics":[161],"from":[162,175],"hundreds":[163],"customers":[165,185],"using":[166],"product,":[168],"we":[169],"achieve":[170],"additional":[172],"2X":[173],"beyond":[178],"local":[181],"enables":[184],"replicate":[187],"would":[190],"otherwise":[191],"fail":[192],"complete":[194],"within":[195],"their":[196],"window.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
