{"id":"https://openalex.org/W4400921863","doi":"https://doi.org/10.1186/s40537-024-00964-z","title":"Predictive modelling of MapReduce job performance in cloud environments using machine learning techniques","display_name":"Predictive modelling of MapReduce job performance in cloud environments using machine learning techniques","publication_year":2024,"publication_date":"2024-07-23","ids":{"openalex":"https://openalex.org/W4400921863","doi":"https://doi.org/10.1186/s40537-024-00964-z"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-024-00964-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00964-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00964-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00964-z","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068402780","display_name":"Mohammed Bergui","orcid":"https://orcid.org/0000-0001-7300-7965"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Mohammed Bergui","raw_affiliation_strings":["Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010196807","display_name":"Soufiane Hourri","orcid":"https://orcid.org/0000-0001-6349-4560"},"institutions":[{"id":"https://openalex.org/I119856527","display_name":"Cadi Ayyad University","ror":"https://ror.org/04xf6nm78","country_code":"MA","type":"education","lineage":["https://openalex.org/I119856527"]},{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Soufiane Hourri","raw_affiliation_strings":["Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco","Laboratory of Process, Industrial Signals and Computer Science, Higher School of Technology, University of Cadi Ayyad, Safi, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]},{"raw_affiliation_string":"Laboratory of Process, Industrial Signals and Computer Science, Higher School of Technology, University of Cadi Ayyad, Safi, Morocco","institution_ids":["https://openalex.org/I119856527"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838443","display_name":"Sa\u00efd Najah","orcid":"https://orcid.org/0000-0002-4169-3443"},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Said Najah","raw_affiliation_strings":["Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Systems and Applications, Department of Computer Science, Faculty of Sciences and Technologies, University of Sidi Mohammed Ben Abdellah, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088624697","display_name":"Nikola S. Nikolov","orcid":"https://orcid.org/0000-0001-8022-0297"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Nikola S. Nikolov","raw_affiliation_strings":["Department of Computer Science and Information Systems, University of Limerick, Limerick, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068402780"],"corresponding_institution_ids":["https://openalex.org/I81605866"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":3.6668,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93777886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"11","issue":"1","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":0.9995999932289124,"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":0.9995999932289124,"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":0.9955999851226807,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9825999736785889,"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/computer-science","display_name":"Computer science","score":0.878606915473938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6958168148994446},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6759966611862183},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6626086235046387},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5460824966430664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.545140266418457},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5247609615325928},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5113903880119324},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4794687032699585},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.43965500593185425},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4321509301662445},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.16980630159378052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878606915473938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6958168148994446},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6759966611862183},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6626086235046387},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5460824966430664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545140266418457},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5247609615325928},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5113903880119324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4794687032699585},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.43965500593185425},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4321509301662445},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.16980630159378052},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-024-00964-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00964-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00964-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a83f2a1fa96143278bcaacc701de996f","is_oa":false,"landing_page_url":"https://doaj.org/article/a83f2a1fa96143278bcaacc701de996f","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 11, Iss 1, Pp 1-20 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-024-00964-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00964-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00964-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400921863.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1582576952","https://openalex.org/W1982363918","https://openalex.org/W1999357043","https://openalex.org/W2002472616","https://openalex.org/W2040141901","https://openalex.org/W2059878010","https://openalex.org/W2074935284","https://openalex.org/W2105947650","https://openalex.org/W2110086534","https://openalex.org/W2114896543","https://openalex.org/W2118566694","https://openalex.org/W2122950698","https://openalex.org/W2173213060","https://openalex.org/W2238447664","https://openalex.org/W2284241005","https://openalex.org/W2417588233","https://openalex.org/W2527795289","https://openalex.org/W2990017454","https://openalex.org/W2995564009","https://openalex.org/W2999063186","https://openalex.org/W3004078591","https://openalex.org/W3039741259","https://openalex.org/W3102378867","https://openalex.org/W4322746292"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W4366990902","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W4317732970","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W4388550696"],"abstract_inverted_index":{"Abstract":[0],"Within":[1],"the":[2,18,54,82,112,117,129],"Hadoop":[3,40,76,162],"ecosystem,":[4],"MapReduce":[5,58,77],"stands":[6],"as":[7,116,135],"a":[8,31,47,70,92],"cornerstone":[9],"for":[10,23,52,164],"managing,":[11],"processing,":[12],"and":[13,37,66,88,106,124,138,155],"mining":[14],"large-scale":[15,165],"datasets.":[16],"Yet,":[17],"absence":[19],"of":[20,26,57,95,132,160],"efficient":[21],"solutions":[22],"precise":[24],"estimation":[25],"job":[27,78,89,143],"execution":[28,55],"times":[29],"poses":[30],"persistent":[32],"challenge,":[33],"impacting":[34],"task":[35],"allocation":[36,140],"distribution":[38],"within":[39],"clusters.":[41],"In":[42],"this":[43,146],"study,":[44],"we":[45,80,110,148],"present":[46],"comprehensive":[48,75],"machine":[49,96],"learning":[50,97],"approach":[51],"predicting":[53],"time":[56],"jobs,":[59],"encompassing":[60],"data":[61,136,166],"collection,":[62],"preprocessing,":[63],"feature":[64],"engineering,":[65],"model":[67,115],"evaluation.":[68],"Leveraging":[69],"rich":[71],"dataset":[72],"derived":[73],"from":[74],"traces,":[79],"explore":[81],"intricate":[83],"relationship":[84],"between":[85],"cluster":[86],"parameters":[87],"performance.":[90,144],"Through":[91],"comparative":[93],"analysis":[94],"models,":[98],"including":[99],"linear":[100],"regression,":[101],"decision":[102],"tree,":[103],"random":[104,113],"forest,":[105],"gradient-boosted":[107],"regression":[108],"trees,":[109],"identify":[111],"forest":[114],"most":[118],"effective,":[119],"demonstrating":[120],"superior":[121],"predictive":[122],"accuracy":[123],"robustness.":[125],"Our":[126],"findings":[127],"underscore":[128],"critical":[130],"role":[131],"features":[133],"such":[134],"size":[137],"resource":[139,152],"in":[141],"determining":[142],"With":[145],"work,":[147],"aim":[149],"to":[150],"enhance":[151],"management":[153],"efficiency":[154],"enable":[156],"more":[157],"effective":[158],"utilisation":[159],"cloud-based":[161],"clusters":[163],"processing":[167],"tasks.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}