{"id":"https://openalex.org/W2754702117","doi":"https://doi.org/10.4233/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","title":"Optimizing the Performance of Data Analytics Frameworks","display_name":"Optimizing the Performance of Data Analytics Frameworks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2754702117","doi":"https://doi.org/10.4233/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","mag":"2754702117"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","pdf_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009413742","display_name":"Bogdan Ghi\u021b","orcid":"https://orcid.org/0000-0002-2530-8736"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"B.I. Ghit","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009413742"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16460234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9944999814033508,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8471382260322571},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6759570240974426},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6267220377922058},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5678890943527222},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.47924235463142395},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.47572091221809387},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.4745405912399292},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4543953239917755},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4532639682292938},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4497626721858978},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.413014680147171},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16918593645095825},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13778170943260193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471382260322571},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6759570240974426},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6267220377922058},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5678890943527222},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.47924235463142395},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.47572091221809387},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.4745405912399292},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4543953239917755},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4532639682292938},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4497626721858978},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.413014680147171},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16918593645095825},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13778170943260193},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","pdf_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"doi:10.4233/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","is_oa":true,"landing_page_url":"https://doi.org/10.4233/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"},{"id":"mag:2754702117","is_oa":false,"landing_page_url":"https://repository.tudelft.nl/islandora/object/uuid%3A2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","pdf_url":"http://resolver.tudelft.nl/uuid:2d9ac8e0-b922-4fcc-a33d-44a67f7bffad","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2754702117.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2765482786","https://openalex.org/W3104673016","https://openalex.org/W2166796787","https://openalex.org/W2286822343","https://openalex.org/W2899127905","https://openalex.org/W3174027993","https://openalex.org/W3038827379","https://openalex.org/W2522087492","https://openalex.org/W3094532081","https://openalex.org/W2907782912","https://openalex.org/W2342858114","https://openalex.org/W2798032864","https://openalex.org/W3186637328","https://openalex.org/W2095196235","https://openalex.org/W2559872089","https://openalex.org/W2168657694","https://openalex.org/W2989710264","https://openalex.org/W3213020641","https://openalex.org/W2344428592","https://openalex.org/W2125775320"],"abstract_inverted_index":{"Data":[0],"analytics":[1,59,111],"frameworks":[2,26,112,149],"enable":[3],"users":[4,132,160],"to":[5,156,216,220,229],"process":[6],"large":[7,19,129,188],"datasets":[8],"while":[9],"hiding":[10],"the":[11,28,31,49,54,106,191,202,206,242,250,264,284],"complexity":[12],"of":[13,21,23,48,53,71,82,94,109,131,190,208,252,266,297],"scaling":[14],"out":[15],"their":[16,39,136,157],"computations":[17,55],"on":[18,46],"clusters":[20],"thousands":[22],"machines.":[24],"Such":[25],"parallelize":[27],"computations,":[29],"distribute":[30],"data,":[32],"and":[33,43,64,79,91,236,261,278,289],"tolerate":[34],"server":[35],"failures":[36,209],"by":[37,57,113,293],"deploying":[38],"own":[40],"runtime":[41],"systems":[42],"distributed":[44],"filesystems":[45],"subsets":[47],"datacenter":[50,192],"resources.":[51,178],"Most":[52],"required":[56],"data":[58,110],"applications":[60],"are":[61,247],"conceptually":[62],"straight-forward":[63],"can":[65],"be":[66,197],"performed":[67],"through":[68],"massive":[69],"parallelization":[70],"jobs":[72,173,185,195],"into":[73],"many":[74],"fine-grained":[75],"tasks.":[76],"Providing":[77],"efficient":[78],"fault-tolerant":[80],"execution":[81],"these":[83,166,231],"tasks":[84],"in":[85,120,205,272],"datacenters":[86],"is":[87,125,145,210],"ever":[88],"more":[89],"challenging":[90],"a":[92,128,182,273],"variety":[93],"opportunities":[95],"for":[96,172,241],"performance":[97,108,143,204,265],"optimization":[98],"still":[99],"exist.":[100],"In":[101,227],"this":[102],"thesis":[103],"we":[104,214,233,262,282],"optimize":[105],"job":[107,203],"addressing":[114],"several":[115,238],"fundamental":[116],"challenges":[117,232],"that":[118,174,186,246],"arise":[119],"datacenters.":[121],"The":[122],"first":[123],"challenge":[124],"multi-tenancy:":[126],"having":[127],"number":[130],"may":[133,150,196],"require":[134,175],"isolating":[135],"workloads":[137,277],"across":[138],"multiple":[139],"frameworks.":[140],"Nevertheless,":[141],"achieving":[142],"isolation":[144],"difficult,":[146],"because":[147],"different":[148],"deliver":[151],"very":[152,163],"unbalanced":[153],"service":[154],"levels":[155],"users.":[158],"Second,":[159],"have":[161],"become":[162],"demanding":[164],"from":[165,249],"frameworks,":[167],"thus":[168],"expecting":[169],"timely":[170],"results":[171],"only":[176],"limited":[177],"However,":[179],"even":[180],"with":[181,269],"few":[183],"long":[184],"consume":[187],"fractions":[189],"resources,":[193],"short":[194],"delayed":[198],"significantly.":[199],"Third,":[200],"improving":[201],"face":[207],"harder":[211],"still,":[212],"as":[213],"need":[215],"allocate":[217],"extra":[218],"resources":[219],"recompute":[221],"work":[222,292],"which":[223],"was":[224],"already":[225],"done.":[226],"order":[228],"address":[230],"design,":[234],"implement,":[235],"test":[237],"scheduling":[239,298],"policies":[240,268],"evolving":[243],"usage":[244],"trends":[245],"derived":[248],"analysis":[251],"basic":[253],"theoretical":[254,291],"models.":[255],"We":[256],"take":[257],"an":[258],"experimental":[259],"approach":[260],"evaluate":[263],"our":[267],"real-world":[270],"experiments":[271,288],"datacenter,":[274],"using":[275],"representative":[276],"standard":[279],"benchmarks.":[280],"Furthermore,":[281],"bridge":[283],"gap":[285],"between":[286],"those":[287],"prior":[290],"performing":[294],"large-scale":[295],"simulations":[296],"policies.":[299]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
