{"id":"https://openalex.org/W4387068060","doi":"https://doi.org/10.1109/tc.2023.3318404","title":"Applying Delta Compression to Packed Datasets for Efficient Data Reduction","display_name":"Applying Delta Compression to Packed Datasets for Efficient Data Reduction","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387068060","doi":"https://doi.org/10.1109/tc.2023.3318404"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3318404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3318404","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","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":"https://openalex.org/A5100387027","display_name":"Yucheng Zhang","orcid":"https://orcid.org/0000-0001-7716-1214"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I4390039277","display_name":"Yuzhang Normal University","ror":"https://ror.org/03mqkaa34","country_code":null,"type":"education","lineage":["https://openalex.org/I4390039277"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Zhang","raw_affiliation_strings":["School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","School of Mathematics and Computer, Yuzhang Normal University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0001-7716-1214","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]},{"raw_affiliation_string":"School of Mathematics and Computer, Yuzhang Normal University, Nanchang, China","institution_ids":["https://openalex.org/I4390039277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-1477-9751","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072362529","display_name":"Chunzhi Wang","orcid":"https://orcid.org/0000-0002-6742-3644"},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunzhi Wang","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6742-3644","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004584268","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0002-0541-8612"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0002-0541-8612","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085317975","display_name":"Meng Chen","orcid":"https://orcid.org/0009-0009-3707-3784"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Chen","raw_affiliation_strings":["School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China"],"raw_orcid":"https://orcid.org/0009-0009-3707-3784","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012846519","display_name":"Yongxuan Zhang","orcid":"https://orcid.org/0000-0003-3535-0695"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I4390039277","display_name":"Yuzhang Normal University","ror":"https://ror.org/03mqkaa34","country_code":null,"type":"education","lineage":["https://openalex.org/I4390039277"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxuan Zhang","raw_affiliation_strings":["School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","School of Mathematics and Computer, Yuzhang Normal University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0003-3535-0695","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]},{"raw_affiliation_string":"School of Mathematics and Computer, Yuzhang Normal University, Nanchang, China","institution_ids":["https://openalex.org/I4390039277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350655","display_name":"Zhang Le","orcid":"https://orcid.org/0009-0007-7028-4319"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China"],"raw_orcid":"https://orcid.org/0009-0007-7028-4319","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":2.147,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90492328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"73","issue":"1","first_page":"73","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9980999827384949,"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":0.9980999827384949,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9580000042915344,"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/T11478","display_name":"Caching and Content Delivery","score":0.9476000070571899,"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":0.9481357336044312},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9315787553787231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8196738362312317},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6910896897315979},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6745667457580566},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5229864120483398},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4396202564239502},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4243409335613251},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4190787971019745},{"id":"https://openalex.org/keywords/backup-software","display_name":"Backup software","score":0.4159410297870636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3282257318496704}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.9481357336044312},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9315787553787231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196738362312317},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6910896897315979},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6745667457580566},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5229864120483398},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4396202564239502},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4243409335613251},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4190787971019745},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.4159410297870636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3282257318496704},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2023.3318404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3318404","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1419542150","display_name":null,"funder_award_id":"JXSQ2023201022","funder_id":"https://openalex.org/F3692415409","funder_display_name":"Double Thousand Plan of Jiangxi Province"},{"id":"https://openalex.org/G1727559519","display_name":null,"funder_award_id":"62262042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1740210924","display_name":null,"funder_award_id":"20224ABC03A01","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"},{"id":"https://openalex.org/G3365248950","display_name":null,"funder_award_id":"20224BAB202017","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"},{"id":"https://openalex.org/G827283038","display_name":null,"funder_award_id":"62271239","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F3692415409","display_name":"Double Thousand Plan of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W152583591","https://openalex.org/W1947728686","https://openalex.org/W2010150514","https://openalex.org/W2033062224","https://openalex.org/W2039843652","https://openalex.org/W2063547430","https://openalex.org/W2073370301","https://openalex.org/W2112671267","https://openalex.org/W2124632914","https://openalex.org/W2148885851","https://openalex.org/W2172174733","https://openalex.org/W2343548694","https://openalex.org/W2800515890","https://openalex.org/W2810972659","https://openalex.org/W2909888707","https://openalex.org/W3006159724","https://openalex.org/W3023701944","https://openalex.org/W3174127842","https://openalex.org/W6600228218","https://openalex.org/W6600884019","https://openalex.org/W6602837329","https://openalex.org/W6604953292","https://openalex.org/W6605032692","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6628275343","https://openalex.org/W6628419871","https://openalex.org/W6634463810","https://openalex.org/W6636638921","https://openalex.org/W6638528349","https://openalex.org/W6640739288","https://openalex.org/W6683485282","https://openalex.org/W6687744917","https://openalex.org/W6705331335","https://openalex.org/W6735783352","https://openalex.org/W6749584455","https://openalex.org/W6759234905","https://openalex.org/W6760689153","https://openalex.org/W6790796689"],"related_works":["https://openalex.org/W2939925694","https://openalex.org/W2354454611","https://openalex.org/W2348132657","https://openalex.org/W4285245558","https://openalex.org/W2952411620","https://openalex.org/W2012359782","https://openalex.org/W4301155776","https://openalex.org/W2375056709","https://openalex.org/W2048606985","https://openalex.org/W1437397736"],"abstract_inverted_index":{"Backup":[0],"systems":[1],"often":[2,12],"adopt":[3],"deduplication":[4],"techniques":[5],"for":[6,71,126],"data":[7],"reduction.":[8],"Real-world":[9],"backup":[10,66,190],"products":[11],"group":[13],"files":[14],"into":[15],"larger":[16],"units":[17],"(called":[18],"packed":[19,38,81],"files)":[20],"before":[21,30],"deduplicating":[22],"them.":[23],"The":[24],"grouping":[25],"entails":[26],"inserting":[27],"metadata":[28,41,109],"immediately":[29],"the":[31,37,127,149,189],"contents":[32],"of":[33,133],"each":[34,113],"file":[35],"in":[36,76],"file.":[39],"Some":[40],"change":[42],"with":[43,144,173],"every":[44,93],"backup,":[45],"producing":[46],"substantial":[47],"similar":[48,58,111,129],"(non-duplicate)":[49],"chunks.":[50],"Delta":[51],"compression":[52,125,182],"can":[53],"remove":[54],"redundancy":[55],"among":[56],"those":[57],"chunks":[59,74,89,130,141],"but":[60,110,194],"cannot":[61],"be":[62],"applied":[63],"to":[64,107,112,121,166],"HDD-based":[65],"storage":[67],"because":[68],"I/Os":[69,151],"required":[70],"fetching":[72],"base":[73,140],"result":[75],"severe":[77],"throughput":[78,191],"loss.":[79],"For":[80],"datasets,":[82],"some":[83],"duplicate":[84],"chunks,":[85],"called":[86],"persistent":[87],"fragmented":[88],"(PFCs),":[90],"are":[91,104],"rewritten":[92],"backup.":[94],"We":[95,158],"observe":[96],"that":[97,178],"corresponding":[98],"chunk":[99],"pairs":[100],"surrounding":[101],"identical":[102],"PFCs":[103,145],"non-identical":[105],"due":[106],"different":[108],"other.":[114],"In":[115],"this":[116],"article,":[117],"we":[118],"propose":[119,160],"PFC-delta":[120,135,179],"perform":[122],"high-performance":[123],"delta":[124,163],"aforementioned":[128],"on":[131,148,192],"top":[132],"deduplication.":[134],"identifies":[136],"and":[137,184],"prefetches":[138],"potential":[139],"stored":[142],"along":[143],"by":[146],"piggybacking":[147],"routine":[150],"during":[152],"deduplication,":[153],"thus":[154],"avoiding":[155],"extra":[156,168],"I/Os.":[157],"also":[159],"a":[161],"hash-less":[162],"encoding":[164],"approach":[165],"reduce":[167],"computational":[169],"overheads.":[170],"Evaluation":[171],"results":[172],"four":[174],"real-world":[175],"datasets":[176],"show":[177],"improves":[180],"both":[181],"ratio":[183],"restore":[185],"performance,":[186],"while":[187],"increasing":[188],"all":[193],"one":[195],"datasets.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}