{"id":"https://openalex.org/W3124475485","doi":"https://doi.org/10.3390/sym13020195","title":"Choosing a Data Storage Format in the Apache Hadoop System Based on Experimental Evaluation Using Apache Spark","display_name":"Choosing a Data Storage Format in the Apache Hadoop System Based on Experimental Evaluation Using Apache Spark","publication_year":2021,"publication_date":"2021-01-26","ids":{"openalex":"https://openalex.org/W3124475485","doi":"https://doi.org/10.3390/sym13020195","mag":"3124475485"},"language":"en","primary_location":{"id":"doi:10.3390/sym13020195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13020195","pdf_url":"https://www.mdpi.com/2073-8994/13/2/195/pdf?version=1612331658","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/13/2/195/pdf?version=1612331658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002035967","display_name":"V. Belov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110371","display_name":"Russian Academy of Education","ror":"https://ror.org/026s4j722","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110371"]},{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Belov","raw_affiliation_strings":["Data Center, Russian Academy of Education, 119121 Moscow, Russia","Department of Intelligent Information Security Systems, MIREA\u2014Russian Technological University, 119454 Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Center, Russian Academy of Education, 119121 Moscow, Russia","institution_ids":["https://openalex.org/I4210110371"]},{"raw_affiliation_string":"Department of Intelligent Information Security Systems, MIREA\u2014Russian Technological University, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061165704","display_name":"\u0410. \u0418. \u0422\u0430\u0442\u0430\u0440\u0438\u043d\u0446\u0435\u0432","orcid":"https://orcid.org/0000-0003-2969-8740"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Tatarintsev","raw_affiliation_strings":["Departments of Higher Mathematics 2, MIREA\u2014Russian Technological University, 119454 Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Higher Mathematics 2, MIREA\u2014Russian Technological University, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015510338","display_name":"Evgeny Nikulchev","orcid":"https://orcid.org/0000-0003-1254-9132"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Evgeny Nikulchev","raw_affiliation_strings":["Department of Intelligent Information Security Systems, MIREA\u2014Russian Technological University, 119454 Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0003-1254-9132","affiliations":[{"raw_affiliation_string":"Department of Intelligent Information Security Systems, MIREA\u2014Russian Technological University, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015510338"],"corresponding_institution_ids":["https://openalex.org/I4210135186"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":3.9553,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93903537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"13","issue":"2","first_page":"195","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9930999875068665,"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":0.9930999875068665,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9757000207901001,"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/spark","display_name":"SPARK (programming language)","score":0.8816088438034058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907571792602539},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7308800220489502},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.7280239462852478},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6645820140838623},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5470425486564636},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5432568192481995},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4815676212310791},{"id":"https://openalex.org/keywords/data-format","display_name":"Data format","score":0.476043701171875},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4386783540248871},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17765837907791138},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10182711482048035}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8816088438034058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907571792602539},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7308800220489502},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.7280239462852478},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6645820140838623},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5470425486564636},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5432568192481995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4815676212310791},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.476043701171875},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4386783540248871},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17765837907791138},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10182711482048035},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym13020195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13020195","pdf_url":"https://www.mdpi.com/2073-8994/13/2/195/pdf?version=1612331658","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9ad93c98733a4bdaa6b045ca37d71a00","is_oa":true,"landing_page_url":"https://doaj.org/article/9ad93c98733a4bdaa6b045ca37d71a00","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 13, Iss 2, p 195 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/13/2/195/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym13020195","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym13020195","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13020195","pdf_url":"https://www.mdpi.com/2073-8994/13/2/195/pdf?version=1612331658","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3124475485.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1599861493","https://openalex.org/W2158056686","https://openalex.org/W2189465200","https://openalex.org/W2215252103","https://openalex.org/W2479679926","https://openalex.org/W2530314904","https://openalex.org/W2539685938","https://openalex.org/W2548753368","https://openalex.org/W2556483642","https://openalex.org/W2610704076","https://openalex.org/W2735847081","https://openalex.org/W2898707002","https://openalex.org/W2904062940","https://openalex.org/W2908094560","https://openalex.org/W2943941948","https://openalex.org/W2957640084","https://openalex.org/W2963122011","https://openalex.org/W2968098918","https://openalex.org/W2982333937","https://openalex.org/W3014560542","https://openalex.org/W3041787869","https://openalex.org/W3045741511","https://openalex.org/W3094558061","https://openalex.org/W3099235704","https://openalex.org/W3103287883","https://openalex.org/W3110338955","https://openalex.org/W4232539307","https://openalex.org/W4394647895","https://openalex.org/W6635818143","https://openalex.org/W6687322159","https://openalex.org/W6688549355","https://openalex.org/W6864356403"],"related_works":["https://openalex.org/W2577820972","https://openalex.org/W2388737859","https://openalex.org/W3201630298","https://openalex.org/W2541607450","https://openalex.org/W197262582","https://openalex.org/W3023957151","https://openalex.org/W2391941239","https://openalex.org/W2239835736","https://openalex.org/W2365783963","https://openalex.org/W3088950643"],"abstract_inverted_index":{"One":[0],"of":[1,6,27,34,62,92,96,110,137,145,188,196,203,205],"the":[2,15,24,32,36,43,49,70,86,93,97,104,119,138,151,160,167,173,177,189,194,210],"most":[3,51],"important":[4],"tasks":[5],"any":[7],"platform":[8],"for":[9,23,54,68,128,156,171,199,209],"big":[10,28,56,130],"data":[11,16,38,74,131,146,206],"processing":[12,129,154],"is":[13,191],"storing":[14,55],"received.":[17],"Different":[18],"systems":[19],"have":[20],"different":[21,157],"requirements":[22],"storage":[25,39,75,147,207],"formats":[26,53,64,76,99,112,208],"data,":[29,57],"which":[30],"raises":[31],"problem":[33],"choosing":[35,69,172],"optimal":[37,174],"format":[40,175],"to":[41,141],"solve":[42],"current":[44],"problem.":[45],"This":[46],"paper":[47],"describes":[48],"five":[50],"popular":[52],"presents":[58],"an":[59,107,121,169,216],"experimental":[60,108,122,217],"evaluation":[61,109],"these":[63,111],"and":[65,115,153],"a":[66,89,197,201],"methodology":[67],"format.":[71],"The":[72,135,186],"following":[73],"will":[77],"be":[78],"considered:":[79],"avro,":[80],"CSV,":[81],"JSON,":[82],"ORC,":[83],"parquet.":[84],"At":[85],"first":[87],"stage,":[88,106],"comparative":[90],"analysis":[91],"main":[94],"characteristics":[95,144],"studied":[98],"was":[100,113,124,140,180],"carried":[101,116],"out;":[102],"at":[103],"second":[105],"prepared":[114],"out.":[117],"For":[118],"experiment,":[120],"stand":[123],"deployed":[125],"with":[126],"tools":[127],"installed":[132],"on":[133,215],"it.":[134],"aim":[136],"experiment":[139],"find":[142],"out":[143],"formats,":[148],"such":[149],"as":[150],"volume":[152],"speed":[155],"operations":[158],"using":[159,182,219],"Apache":[161,211,220],"Spark":[162],"framework.":[163],"In":[164],"addition,":[165],"within":[166],"study,":[168],"algorithm":[170],"from":[176],"presented":[178,192],"alternatives":[179],"developed":[181],"tropical":[183],"optimization":[184],"methods.":[185],"result":[187],"study":[190],"in":[193],"form":[195],"technique":[198],"obtaining":[200],"vector":[202],"ratings":[204],"Hadoop":[212],"system,":[213],"based":[214],"assessment":[218],"Spark.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
