{"id":"https://openalex.org/W3207701870","doi":"https://doi.org/10.1109/icc45855.2022.9838782","title":"Model-Based Reinforcement Learning Framework of Online Network Resource Allocation","display_name":"Model-Based Reinforcement Learning Framework of Online Network Resource Allocation","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W3207701870","doi":"https://doi.org/10.1109/icc45855.2022.9838782","mag":"3207701870"},"language":"en","primary_location":{"id":"doi:10.1109/icc45855.2022.9838782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/ICC45855.2022.9838782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045179526","display_name":"Bahador Bakhshi","orcid":"https://orcid.org/0000-0003-1365-3185"},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Bahador Bakhshi","raw_affiliation_strings":["Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA),Spain","Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA),Spain","institution_ids":["https://openalex.org/I4210087295"]},{"raw_affiliation_string":"Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA), Spain","institution_ids":["https://openalex.org/I4210087295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041598687","display_name":"Josep Mangues\u2010Bafalluy","orcid":"https://orcid.org/0000-0003-4960-9434"},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Mangues-Bafalluy","raw_affiliation_strings":["Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA),Spain","Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA),Spain","institution_ids":["https://openalex.org/I4210087295"]},{"raw_affiliation_string":"Centre Tecnologic de Telecomunicacions de Catalunya (CTTC/CERCA), Spain","institution_ids":["https://openalex.org/I4210087295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087295"],"apc_list":null,"apc_paid":null,"fwci":2.4781,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88420155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4456","last_page":"4461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.996399998664856,"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/T13553","display_name":"Age of Information Optimization","score":0.9937999844551086,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.889162540435791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8108798265457153},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.5516756176948547},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.5379000902175903},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5221600532531738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4514630138874054},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.41973596811294556},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3645564317703247},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.34220391511917114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33123528957366943},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2741714119911194},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09049192070960999}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.889162540435791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108798265457153},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.5516756176948547},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5379000902175903},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5221600532531738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514630138874054},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.41973596811294556},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3645564317703247},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.34220391511917114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33123528957366943},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2741714119911194},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09049192070960999},{"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:10.1109/icc45855.2022.9838782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:7432563","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICC45855.2022.9838782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE International Conference on Communications, ICC 2022","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7432563","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICC45855.2022.9838782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE International Conference on Communications, ICC 2022","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1549353711","https://openalex.org/W1609461728","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2580909119","https://openalex.org/W2753412869","https://openalex.org/W2920362155","https://openalex.org/W2963000651","https://openalex.org/W2973449430","https://openalex.org/W2982539992","https://openalex.org/W3013458912","https://openalex.org/W3015366655","https://openalex.org/W3016325548","https://openalex.org/W3038458067","https://openalex.org/W3038822267","https://openalex.org/W3065783609","https://openalex.org/W3091825588","https://openalex.org/W3094198577","https://openalex.org/W3116945260","https://openalex.org/W3135815554","https://openalex.org/W3185035147","https://openalex.org/W6636452984","https://openalex.org/W6760405395","https://openalex.org/W6779886411","https://openalex.org/W6788213681"],"related_works":["https://openalex.org/W2941957272","https://openalex.org/W2102496746","https://openalex.org/W2360147445","https://openalex.org/W2923452570","https://openalex.org/W206598027","https://openalex.org/W2978610750","https://openalex.org/W2022931285","https://openalex.org/W1589966275","https://openalex.org/W2086872282","https://openalex.org/W2137789903"],"abstract_inverted_index":{"Online":[0],"Network":[1],"Resource":[2],"Allocation":[3],"(ONRA)":[4],"for":[5,64,152,209],"service":[6,135,199,210],"provisioning":[7],"is":[8,23,58,71,117,189],"a":[9,16,42,59,143,153],"fundamental":[10],"problem":[11,201],"in":[12,95,120,134,171,177],"communication":[13],"networks.":[14],"As":[15],"sequential":[17],"decision-making":[18],"under":[19],"uncertainty":[20],"problem,":[21],"it":[22,70],"promising":[24],"to":[25,52,61,74,81,100,202,220],"approach":[26],"ONRA":[27,65,122,156],"via":[28,166,205],"Reinforcement":[29],"Learning":[30],"(RL).":[31],"But,":[32],"RL":[33,63,77,151,228],"solutions":[34],"suffer":[35],"from":[36],"the":[37,48,76,90,96,106,110,124,129,132,168,175,183,186,197,225],"sample":[38,164],"complexity":[39],"issue;":[40],"i.e.,":[41],"large":[43],"number":[44],"of":[45,83,105,155,185],"interactions":[46],"with":[47,131,158],"environment":[49],"are":[50],"needed":[51],"find":[53],"an":[54],"efficient":[55],"policy.":[56],"This":[57],"barrier":[60],"utilize":[62],"as":[66],"on":[67,89,196],"one":[68],"hand,":[69,92],"not":[72],"practical":[73],"train":[75],"agent":[78,125],"offline":[79],"due":[80],"lack":[82],"information":[84],"about":[85],"future":[86],"requests,":[87],"and":[88,173,218],"other":[91],"online":[93],"training":[94],"real":[97,192],"network":[98],"leads":[99],"significant":[101],"performance":[102,115,222],"loss":[103],"because":[104],"sub-optimal":[107],"policy":[108,130,176],"during":[109],"prolonged":[111],"learning":[112,216],"time.":[113],"The":[114],"degradation":[116],"even":[118],"higher":[119],"non-stationary":[121],"where":[123],"should":[126],"continually":[127],"adapt":[128],"changes":[133],"requests.":[136],"To":[137],"address":[138],"this":[139],"issue,":[140],"we":[141],"develop":[142],"general":[144],"resource":[145],"allocation":[146],"framework,":[147],"RADAR,":[148],"using":[149,179],"model-based":[150],"class":[154],"problems":[157],"known":[159],"immediate":[160],"rewards.":[161],"RADAR":[162,195],"improves":[163],"efficiency":[165],"exploring":[167],"state":[169],"space":[170],"background":[172],"exploiting":[174],"decisiontime":[178],"synthetic":[180],"samples":[181],"by":[182,191],"model":[184],"environment,":[187],"which":[188],"trained":[190],"interactions.":[193],"Applying":[194],"multi-domain":[198],"federation":[200],"maximize":[203],"profit":[204],"selecting":[206],"proper":[207],"domains":[208],"requests":[211],"deployment,":[212],"shows":[213],"its":[214],"continual":[215],"capability":[217],"up":[219],"44%":[221],"improvement":[223],"w.r.t.":[224],"standard":[226],"model-free":[227],"solution.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}