{"id":"https://openalex.org/W3139290680","doi":"https://doi.org/10.1109/bigdata50022.2020.9377841","title":"A middle-ware approach to leverage the distributed data de-duplication capability on HPC and Cloud storage systems","display_name":"A middle-ware approach to leverage the distributed data de-duplication capability on HPC and Cloud storage systems","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3139290680","doi":"https://doi.org/10.1109/bigdata50022.2020.9377841","mag":"3139290680"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5079936580","display_name":"Hsing-bung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hsing-bung Chen","raw_affiliation_strings":["HPC-Design Group, Los Alamos National Lab, Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"HPC-Design Group, Los Alamos National Lab, Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103954876","display_name":"Sihai Tang","orcid":"https://orcid.org/0000-0002-2438-4163"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sihai tang","raw_affiliation_strings":["CSE Department, University of North texas, Denton, Texas"],"affiliations":[{"raw_affiliation_string":"CSE Department, University of North texas, Denton, Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082758762","display_name":"Song Fu","orcid":"https://orcid.org/0000-0002-7705-0829"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Fu","raw_affiliation_strings":["CSE Department, University of North texas, Denton, Texas"],"affiliations":[{"raw_affiliation_string":"CSE Department, University of North texas, Denton, Texas","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079936580"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":0.1542,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56294481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"104","issue":null,"first_page":"2649","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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":0.9990000128746033,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9976999759674072,"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/T11719","display_name":"Data Quality and Management","score":0.9922000169754028,"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":0.9037082195281982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7604098916053772},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.52369225025177},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4751995801925659},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4749850332736969},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4495594799518585},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4414025843143463},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36176741123199463},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35228925943374634},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2365470826625824}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9037082195281982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7604098916053772},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.52369225025177},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4751995801925659},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4749850332736969},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4495594799518585},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4414025843143463},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36176741123199463},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35228925943374634},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2365470826625824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1505654100","https://openalex.org/W2035415465","https://openalex.org/W2137985407","https://openalex.org/W2156468933","https://openalex.org/W2294268844","https://openalex.org/W2308303010","https://openalex.org/W2351279544","https://openalex.org/W2411107954","https://openalex.org/W2418682648","https://openalex.org/W2475932436","https://openalex.org/W2790174206","https://openalex.org/W2808357789","https://openalex.org/W2889578482","https://openalex.org/W2891308959","https://openalex.org/W2945335752","https://openalex.org/W3139290680","https://openalex.org/W3150827651","https://openalex.org/W4230077428","https://openalex.org/W6654544606","https://openalex.org/W6659177028","https://openalex.org/W6680477498","https://openalex.org/W6698511295","https://openalex.org/W6705331335","https://openalex.org/W6715070937","https://openalex.org/W6717023391","https://openalex.org/W6752689887","https://openalex.org/W6753935038","https://openalex.org/W6792265198"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"The":[0,49],"unprecedented":[1],"growth":[2],"in":[3,11,88],"the":[4,9,46,127,175],"volume":[5],"and":[6,14,25,34,44,61,75,86,101,115,133,154,169,177],"diversity":[7],"of":[8,32,51,65,80,145,179],"data":[10,23,26,53,66,109,146,156,167,171,183],"today's":[12],"HPC":[13,35,166],"Enterprise":[15,170],"computing":[16],"environment":[17],"has":[18],"posted":[19],"challenging":[20],"problems":[21],"on":[22,112,165],"management":[24],"space":[27],"reduction.":[28],"More":[29],"than":[30],"71%":[31],"enterprise":[33],"communities":[36],"are":[37,69,83],"seeking":[38],"de-duplication":[39,54,67,110,132,147,157,184],"technologies":[40],"to":[41,106,173],"reduce":[42],"cost":[43],"increase":[45],"storage":[47,117],"efficiency.":[48],"importance":[50],"applying":[52,180],"techniques":[55],"is":[56],"critical":[57],"for":[58],"active":[59],"research":[60],"development.":[62],"Current":[63],"implementations":[64,82],"systems":[68],"mainly":[70],"hardware":[71],"dependent,":[72,74],"system":[73],"platform":[76],"dependent.":[77],"Also,":[78],"most":[79],"these":[81,142],"proprietary":[84],"software":[85],"not":[87],"open":[89],"source":[90],"domains.":[91],"In":[92],"this":[93,122],"paper,":[94],"we":[95,149,160],"present":[96],"a":[97],"new":[98],"middle-ware":[99,125,185],"design":[100],"implementation":[102],"approach,":[103],"named":[104],"D3M,":[105],"support":[107],"distributed":[108],"feature":[111],"existing":[113],"file":[114],"object":[116],"systems.":[118],"We":[119],"also":[120],"incorporate":[121],"proposed":[123],"D3M":[124],"with":[126],"Redhat's":[128],"Linux":[129],"device":[130],"layer":[131],"compression":[134],"driver,":[135],"called":[136],"VDO":[137],"(Virtual":[138],"Data":[139],"Optimizer).":[140],"With":[141],"two":[143],"layers":[144],"support,":[148],"accommodate":[150],"both":[151],"client":[152],"side":[153],"server-side":[155],"features.":[158],"Finally,":[159],"conduct":[161],"various":[162],"testing":[163],"cases":[164],"sets":[168,172],"illustrate":[174],"benefits":[176],"advantages":[178],"our":[181],"bilayer":[182],"solution.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}