{"id":"https://openalex.org/W4386998168","doi":"https://doi.org/10.1145/3625389","title":"Cost-based Data Prefetching and Scheduling in Big Data Platforms over Tiered Storage Systems","display_name":"Cost-based Data Prefetching and Scheduling in Big Data Platforms over Tiered Storage Systems","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4386998168","doi":"https://doi.org/10.1145/3625389"},"language":"en","primary_location":{"id":"doi:10.1145/3625389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625389","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3625389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010833372","display_name":"Herodotos Herodotou","orcid":"https://orcid.org/0000-0002-8717-1691"},"institutions":[{"id":"https://openalex.org/I163151358","display_name":"Cyprus University of Technology","ror":"https://ror.org/05qt8tf94","country_code":"CY","type":"education","lineage":["https://openalex.org/I163151358"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Herodotos Herodotou","raw_affiliation_strings":["Cyprus University of Technology, Cyprus"],"raw_orcid":"https://orcid.org/0000-0002-8717-1691","affiliations":[{"raw_affiliation_string":"Cyprus University of Technology, Cyprus","institution_ids":["https://openalex.org/I163151358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053819240","display_name":"Elena Kakoulli","orcid":"https://orcid.org/0000-0003-1489-807X"},"institutions":[{"id":"https://openalex.org/I163151358","display_name":"Cyprus University of Technology","ror":"https://ror.org/05qt8tf94","country_code":"CY","type":"education","lineage":["https://openalex.org/I163151358"]},{"id":"https://openalex.org/I4210122463","display_name":"Neapolis University Pafos","ror":"https://ror.org/02kjms144","country_code":"CY","type":"education","lineage":["https://openalex.org/I4210122463"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Elena Kakoulli","raw_affiliation_strings":["Neapolis University Pafos, Cyprus and Cyprus University of Technology, Cyprus"],"raw_orcid":"https://orcid.org/0000-0003-1489-807X","affiliations":[{"raw_affiliation_string":"Neapolis University Pafos, Cyprus and Cyprus University of Technology, Cyprus","institution_ids":["https://openalex.org/I163151358","https://openalex.org/I4210122463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7076,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95206973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"48","issue":"4","first_page":"1","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9995999932289124,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.9001534581184387},{"id":"https://openalex.org/keywords/trident","display_name":"Trident","score":0.766610324382782},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5843918323516846},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5435500144958496},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5357956290245056},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5241844058036804},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4983706474304199},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4564336836338043},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4247358441352844},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41589099168777466},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4114212095737457},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32002782821655273},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29107415676116943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9001534581184387},{"id":"https://openalex.org/C2777909563","wikidata":"https://www.wikidata.org/wiki/Q271628","display_name":"Trident","level":2,"score":0.766610324382782},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5843918323516846},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5435500144958496},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5357956290245056},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5241844058036804},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4983706474304199},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4564336836338043},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4247358441352844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41589099168777466},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4114212095737457},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32002782821655273},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29107415676116943},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3625389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625389","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:ktisis.cut.ac.cy:20.500.14279/32659","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14279/32659","pdf_url":"https://ktisis.cut.ac.cy/bitstream/20.500.14279/32659/1/Herodotou%20et%20al.-2023.pdf","source":{"id":"https://openalex.org/S4306400897","display_name":"Ktisis at Cyprus University of Technology (Cyprus University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I163151358","host_organization_name":"Cyprus University of Technology","host_organization_lineage":["https://openalex.org/I163151358"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3625389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625389","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386998168.pdf","grobid_xml":"https://content.openalex.org/works/W4386998168.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1985790218","https://openalex.org/W1993120508","https://openalex.org/W1997882450","https://openalex.org/W2022678927","https://openalex.org/W2047281923","https://openalex.org/W2076406848","https://openalex.org/W2087942896","https://openalex.org/W2094469165","https://openalex.org/W2096125134","https://openalex.org/W2104993419","https://openalex.org/W2115413107","https://openalex.org/W2258963578","https://openalex.org/W2294316975","https://openalex.org/W2498764059","https://openalex.org/W2517912324","https://openalex.org/W2522680599","https://openalex.org/W2593880849","https://openalex.org/W2750716688","https://openalex.org/W2753062867","https://openalex.org/W2808383901","https://openalex.org/W2911184449","https://openalex.org/W2911320548","https://openalex.org/W2954729276","https://openalex.org/W3022630129","https://openalex.org/W3122383853","https://openalex.org/W3176360741","https://openalex.org/W4231139262","https://openalex.org/W4237397283","https://openalex.org/W4245810980","https://openalex.org/W4246219036","https://openalex.org/W4312847577","https://openalex.org/W6663627914"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2329895846"],"abstract_inverted_index":{"The":[0,20],"use":[1],"of":[2,60,98,159,229],"storage":[3,18,42,61,99,131],"tiering":[4,43],"is":[5,115,200],"becoming":[6],"popular":[7],"in":[8,17,31,145,202,227],"data-intensive":[9],"compute":[10],"clusters":[11],"due":[12],"to":[13,117],"the":[14,58,64,87,157,160,193],"recent":[15],"advancements":[16],"technologies.":[19],"Hadoop":[21,52,206],"Distributed":[22],"File":[23],"System,":[24],"for":[25,68,155,195],"example,":[26],"now":[27,93],"supports":[28],"storing":[29],"data":[30,48,81,91,187],"memory,":[32],"SSDs,":[33],"and":[34,38,53,63,73,84,111,123,130,149,174,205,207,232],"HDDs,":[35],"while":[36,162],"OctopusFS":[37],"hatS":[39],"offer":[40],"fine-grained":[41],"solutions.":[44],"However,":[45],"current":[46],"big":[47],"platforms":[49],"(such":[50],"as":[51,138,218,220],"Spark)":[54],"are":[55,92],"not":[56],"exploiting":[57],"presence":[59],"tiers":[62],"opportunities":[65],"they":[66],"present":[67],"performance":[69,103,231],"optimizations.":[70],"Specifically,":[71],"schedulers":[72,194],"prefetchers":[74],"will":[75],"make":[76,118],"decisions":[77,125],"only":[78],"based":[79,126],"on":[80,95,127],"locality":[82,129],"information":[83],"completely":[85],"ignore":[86],"fact":[88],"that":[89,114,190],"local":[90],"stored":[94],"a":[96,109,139,146,176,185,211],"variety":[97],"media":[100],"with":[101,192],"different":[102],"characteristics.":[104],"This":[105],"article":[106],"presents":[107],"Trident,":[108],"scheduling":[110,137,180],"prefetching":[112,124,188,197],"framework":[113],"designed":[116],"task":[119,136],"assignment,":[120],"resource":[121,171,179],"scheduling,":[122],"both":[128,203],"tier":[132],"information.":[133],"Trident":[134,168,183,199],"formulates":[135],"minimum":[140],"cost":[141],"maximum":[142],"matching":[143],"problem":[144],"bipartite":[147],"graph":[148],"utilizes":[150],"two":[151],"novel":[152],"pruning":[153],"algorithms":[154],"bounding":[156],"size":[158],"graph,":[161],"still":[163],"guaranteeing":[164],"optimality.":[165],"In":[166],"addition,":[167],"extends":[169],"YARN\u2019s":[170],"request":[172],"model":[173],"proposes":[175],"new":[177],"storage-tier-aware":[178],"algorithm.":[181],"Finally,":[182],"includes":[184],"cost-based":[186],"approach":[189],"coordinates":[191],"optimizing":[196],"operations.":[198],"implemented":[201],"Spark":[204],"evaluated":[208],"extensively":[209],"using":[210],"realistic":[212],"workload":[213],"derived":[214],"from":[215],"Facebook":[216],"traces":[217],"well":[219],"an":[221],"industry-validated":[222],"benchmark,":[223],"demonstrating":[224],"significant":[225],"benefits":[226],"terms":[228],"application":[230],"cluster":[233],"efficiency.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-09-02T07:38:04.252551","created_date":"2025-10-10T00:00:00"}
