{"id":"https://openalex.org/W2775818656","doi":"https://doi.org/10.1109/icdm.2017.99","title":"Data Prefetching for Large Tiered Storage Systems","display_name":"Data Prefetching for Large Tiered Storage Systems","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2775818656","doi":"https://doi.org/10.1109/icdm.2017.99","mag":"2775818656"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2017.99","doi":"https://doi.org/10.1109/icdm.2017.99","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2017.99","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5048981968","display_name":"Giovanni Cherubini","orcid":"https://orcid.org/0000-0002-0573-2919","observed_orcids":["https://orcid.org/0000-0002-0573-2919"]},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giovanni Cherubini","raw_affiliation_strings":["IBM Research - Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003257064","display_name":"Yusik Kim","orcid":"https://orcid.org/0000-0002-2921-6433","observed_orcids":["https://orcid.org/0000-0002-2921-6433","https://orcid.org/0000-0002-5366-9459"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusik Kim","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086348882","display_name":"Mark A. Lantz","orcid":"https://orcid.org/0000-0003-3705-3352","observed_orcids":["https://orcid.org/0000-0003-3705-3352"]},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mark Lantz","raw_affiliation_strings":["IBM Research - Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110027428","display_name":"Vinodh Venkatesan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vinodh Venkatesan","raw_affiliation_strings":["IBM Research - Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8667,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.71810411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"823","last_page":"828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0007999999797903001,"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":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-prefetching","display_name":"data prefetching","score":0.9950000047683716},{"id":"https://openalex.org/keywords/access-prediction","display_name":"access prediction","score":0.9200000166893005},{"id":"https://openalex.org/keywords/file-metadata","display_name":"file metadata","score":0.9739999771118164},{"id":"https://openalex.org/keywords/cold-data","display_name":"cold data","score":0.8939999938011169},{"id":"https://openalex.org/keywords/multi-tier-storage","display_name":"multi-tier storage","score":0.6389999985694885},{"id":"https://openalex.org/keywords/storage-latency","display_name":"storage latency","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8688042163848877},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.814551055431366},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.792324423789978},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.6045359373092651},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5262036919593811},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5084868669509888},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49308034777641296},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.43918073177337646},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.43470126390457153},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43167006969451904},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2017.99","doi":"https://doi.org/10.1109/icdm.2017.99","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2017.99","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W104375141","https://openalex.org/W1669311694","https://openalex.org/W2003549201","https://openalex.org/W2036921595","https://openalex.org/W2074417445","https://openalex.org/W2125788329","https://openalex.org/W2147626801","https://openalex.org/W2340946482","https://openalex.org/W4240977821"],"related_works":["https://openalex.org/W2383225277","https://openalex.org/W1637905","https://openalex.org/W7095658355","https://openalex.org/W7098575448","https://openalex.org/W2074417445","https://openalex.org/W3022537591","https://openalex.org/W7104498094","https://openalex.org/W2552793349","https://openalex.org/W1540207844","https://openalex.org/W1723160108"],"abstract_inverted_index":{"In":[0,109],"multi-tier":[1],"storage":[2,38,124],"systems":[3,81],"with":[4,82],"large":[5,83],"amounts":[6,84],"of":[7,10,71,85,99,107,155,196],"data,":[8,90],"most":[9],"the":[11,33,36,100,104,131,141,149,153,178,186,213],"data":[12,34,51,61,74,77,101,138],"is":[13,94],"stored":[14,139],"on":[15,130,192],"inexpensive":[16],"slower":[17,37,53],"tiers":[18,39,54,57],"such":[19],"as":[20,207],"cloud":[21],"or":[22,76],"tape":[23],"to":[24,48,55,103,118,160,204,208],"achieve":[25],"cost":[26],"savings.":[27],"This":[28],"also":[29],"implies":[30],"that":[31,133,148,157],"retrieving":[32],"from":[35,52,115],"incurs":[40],"high":[41],"latency.":[42],"Therefore,":[43],"it":[44],"would":[45],"be":[46,161,164],"beneficial":[47],"proactively":[49],"prefetch":[50],"faster":[56],"by":[58,166,212],"predicting":[59],"future":[60,210],"accesses.":[62],"State-of-the-art":[63],"access":[64,69,92,137,168,187],"prediction":[65],"methods":[66],"typically":[67],"record":[68],"history":[70,93],"individual":[72],"files,":[73],"objects,":[75],"segments.":[78],"However,":[79],"in":[80,122,140,143,170],"infrequently":[86],"accessed":[87,162],"(or":[88],"cold)":[89],"file-level":[91],"often":[95],"unavailable":[96],"for":[97],"much":[98],"due":[102],"low":[105],"frequency":[106],"access.":[108],"this":[110],"paper,":[111],"we":[112,176],"extract":[113],"information":[114],"file":[116,120,171],"metadata":[117],"predict":[119],"accesses":[121,211],"a":[123,144,193],"system.":[125],"The":[126],"proposed":[127],"method":[128],"relies":[129],"hypothesis":[132],"users":[134],"and":[135,147,198],"applications":[136],"system":[142],"given":[145],"context":[146,150],"and,":[151],"therefore,":[152],"set":[154,195],"files":[156],"are":[158,189,201],"likely":[159,209],"can":[163],"identified":[165],"detecting":[167],"patterns":[169,188,200],"metadata.":[172],"As":[173],"an":[174],"application,":[175],"consider":[177],"LOFAR":[179],"radio":[180],"telescope's":[181],"long":[182],"term":[183],"archive,":[184],"where":[185],"learned":[190],"based":[191],"rich":[194],"metadata,":[197],"these":[199],"then":[202],"used":[203],"make":[205],"predictions":[206],"astronomers.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-12-22T00:00:00"}