{"id":"https://openalex.org/W3012448097","doi":"https://doi.org/10.1109/gcwkshps45667.2019.9024368","title":"Alexandria: A Proof-of-Concept Implementation and Evaluation of Generalised Data Deduplication","display_name":"Alexandria: A Proof-of-Concept Implementation and Evaluation of Generalised Data Deduplication","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3012448097","doi":"https://doi.org/10.1109/gcwkshps45667.2019.9024368","mag":"3012448097"},"language":"en","primary_location":{"id":"doi:10.1109/gcwkshps45667.2019.9024368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshps45667.2019.9024368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Globecom Workshops (GC Wkshps)","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/A5019890468","display_name":"Lars B. Nielsen","orcid":"https://orcid.org/0000-0002-6581-3227"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Lars Nielsen","raw_affiliation_strings":["Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019917624","display_name":"Rasmus Vestergaard","orcid":"https://orcid.org/0000-0002-0815-0148"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus Vestergaard","raw_affiliation_strings":["Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010778610","display_name":"Niloofar Yazdani","orcid":"https://orcid.org/0000-0002-3191-1347"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Niloofar Yazdani","raw_affiliation_strings":["Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079244939","display_name":"Prasad Talasila","orcid":"https://orcid.org/0000-0002-8973-2640"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Prasad Talasila","raw_affiliation_strings":["Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110828662","display_name":"Daniel E. Lucani","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel E. Lucani","raw_affiliation_strings":["Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, DIGIT, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000643612","display_name":"M\u00e1rton Sipos","orcid":"https://orcid.org/0000-0003-4671-938X"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Marton Sipos","raw_affiliation_strings":["Department of Automation and Applied Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Automation and Applied Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019890468"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":3.7307,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94349605,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9987000226974487,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9987000226974487,"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":0.9922000169754028,"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/T11719","display_name":"Data Quality and Management","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9763685464859009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.830483078956604},{"id":"https://openalex.org/keywords/proof-of-concept","display_name":"Proof of concept","score":0.5884487628936768},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5124052166938782},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4735773503780365},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.44007280468940735},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.4357272982597351},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4274473786354065},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3649864196777344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20304268598556519},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18054082989692688}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9763685464859009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830483078956604},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.5884487628936768},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5124052166938782},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4735773503780365},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.44007280468940735},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.4357272982597351},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4274473786354065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3649864196777344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20304268598556519},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18054082989692688}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/gcwkshps45667.2019.9024368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshps45667.2019.9024368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/c3e2315b-b376-4bee-b761-778477d06385","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/c3e2315b-b376-4bee-b761-778477d06385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nielsen, L, Vestergaard, R, Yazdani, N, Talasila, S R K P, Lucani R\u00f6tter, D E & Sipos, M 2019, Alexandria: A Proof-of-concept Implementation and Evaluation of Generalised Data Deduplication. in 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings., 9024368, IEEE, 2019 IEEE Globecom Workshops, 09/12/2019. https://doi.org/10.1109/GCWkshps45667.2019.9024368","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W174289249","https://openalex.org/W1877865836","https://openalex.org/W1980073965","https://openalex.org/W2038908732","https://openalex.org/W2055745001","https://openalex.org/W2175342987","https://openalex.org/W2342204193","https://openalex.org/W2475932436","https://openalex.org/W2780813414","https://openalex.org/W2909864759","https://openalex.org/W3102843100","https://openalex.org/W6607057542"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3044766408","https://openalex.org/W3008013744","https://openalex.org/W2884042376","https://openalex.org/W2615141153","https://openalex.org/W2077135008","https://openalex.org/W223870977","https://openalex.org/W2739791894","https://openalex.org/W2912031806","https://openalex.org/W2351285699"],"abstract_inverted_index":{"The":[0],"amount":[1,37],"of":[2,23,25,38,59,77,104,112,122,161],"data":[3,66,110,154],"generated":[4],"worldwide":[5],"is":[6,51],"expected":[7],"to":[8,12,80,119,143,148],"grow":[9],"from":[10],"33":[11],"175":[13],"ZB":[14],"by":[15,20,61],"2025":[16],"in":[17],"part":[18],"driven":[19],"the":[21,57,78,81,101,120,123,130],"growth":[22],"Internet":[24],"Things":[26],"(IoT)":[27],"and":[28,73,95,115,117,125,151],"cyber-physical":[29],"systems":[30],"(CPS).":[31],"To":[32],"cope":[33],"with":[34,153,156],"this":[35],"enormous":[36],"data,":[39],"new":[40,53],"cloud":[41],"storage":[42,60],"techniques":[43],"must":[44],"be":[45],"developed.":[46],"Generalised":[47,105,138],"Data":[48,106,139],"Deduplication":[49,107,140],"(GDD)":[50],"a":[52,74,90,96],"paradigm":[54],"for":[55,84,93],"reducing":[56],"cost":[58],"systematically":[62],"identifying":[63],"near":[64],"identical":[65],"chunks,":[67],"storing":[68],"their":[69],"common":[70],"component":[71],"once,":[72],"compact":[75],"representation":[76],"deviation":[79],"original":[82],"chunk":[83],"each":[85],"chunk.":[86],"This":[87],"paper":[88],"presents":[89],"system":[91],"architecture":[92],"GDD":[94],"proof-of-concept":[97],"implementation.":[98],"We":[99,135],"evaluated":[100],"compression":[102,145],"gain":[103,146],"using":[108],"three":[109],"sets":[111,155],"varying":[113],"size":[114],"content":[116],"compared":[118,147],"performance":[121],"EXT4":[124,150],"ZFS":[126,152],"file":[127],"systems,":[128],"where":[129],"latter":[131],"employs":[132],"classic":[133],"deduplication.":[134],"show":[136],"that":[137],"provide":[141],"up":[142],"16.75%":[144],"both":[149],"less":[157],"than":[158],"5":[159],"GB":[160],"data.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
