{"id":"https://openalex.org/W4412353340","doi":"https://doi.org/10.1109/mcom.001.2500207","title":"Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges","display_name":"Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412353340","doi":"https://doi.org/10.1109/mcom.001.2500207"},"language":"en","primary_location":{"id":"doi:10.1109/mcom.001.2500207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500207","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research-information.bris.ac.uk/en/publications/b5c0a0f9-58c0-4efb-b13f-4a69b194889b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032867183","display_name":"Haiyuan Li","orcid":"https://orcid.org/0000-0001-9786-526X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Haiyuan Li","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094584818","display_name":"Hari Madhukumar","orcid":"https://orcid.org/0009-0002-9390-2734"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hari Madhukumar","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027901096","display_name":"Peizheng Li","orcid":"https://orcid.org/0000-0003-1516-1993"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peizheng Li","raw_affiliation_strings":["Toshiba Europe Ltd.,Bristol Research and Innovation Laboratory,U.K"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd.,Bristol Research and Innovation Laboratory,U.K","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014126601","display_name":"Yuelin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuelin Liu","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028778942","display_name":"Yiran Teng","orcid":"https://orcid.org/0009-0003-3740-691X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiran Teng","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004458037","display_name":"Yulei Wu","orcid":"https://orcid.org/0000-0003-0801-8443"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulei Wu","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387221","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0003-3053-0515"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077858337","display_name":"Shuangyi Yan","orcid":"https://orcid.org/0000-0002-5021-2840"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuangyi Yan","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030580652","display_name":"Dimitra Simeonidou","orcid":"https://orcid.org/0000-0002-7046-544X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitra Simeonidou","raw_affiliation_strings":["University of Bristol,U.K"],"affiliations":[{"raw_affiliation_string":"University of Bristol,U.K","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5032867183"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":1.1617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8006414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"64","issue":"2","first_page":"134","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.7542999982833862,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10917","display_name":"Smart Grid Security and Resilience","score":0.7542999982833862,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.6467999815940857,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8443323373794556},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7150339484214783},{"id":"https://openalex.org/keywords/ran","display_name":"Ran","score":0.6771942973136902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42537981271743774},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.41542771458625793},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4060254693031311},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.3979971408843994},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.328332781791687},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20890316367149353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443323373794556},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7150339484214783},{"id":"https://openalex.org/C160704184","wikidata":"https://www.wikidata.org/wiki/Q18031028","display_name":"Ran","level":2,"score":0.6771942973136902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42537981271743774},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.41542771458625793},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4060254693031311},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.3979971408843994},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.328332781791687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20890316367149353},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mcom.001.2500207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500207","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Magazine","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/b5c0a0f9-58c0-4efb-b13f-4a69b194889b","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/b5c0a0f9-58c0-4efb-b13f-4a69b194889b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, H, Madhukumar, H, Li, P, Liu, Y, Teng, Y, Wu, Y, Wang, N, Yan, S & Simeonidou, D 2025, 'Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges', IEEE Communications Magazine. https://doi.org/10.1109/MCOM.001.2500207","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:research-information.bris.ac.uk:openaire/b5c0a0f9-58c0-4efb-b13f-4a69b194889b","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/b5c0a0f9-58c0-4efb-b13f-4a69b194889b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, H, Madhukumar, H, Li, P, Liu, Y, Teng, Y, Wu, Y, Wang, N, Yan, S & Simeonidou, D 2025, 'Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges', IEEE Communications Magazine. https://doi.org/10.1109/MCOM.001.2500207","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2943464289","display_name":null,"funder_award_id":"EP/X04047X/2,EP/Y037243/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3006765757","https://openalex.org/W3017042178","https://openalex.org/W4213425359","https://openalex.org/W4224303892","https://openalex.org/W4290997040","https://openalex.org/W4292084566","https://openalex.org/W4313855663","https://openalex.org/W4401692170","https://openalex.org/W4403765696","https://openalex.org/W4407566256"],"related_works":["https://openalex.org/W1766728438","https://openalex.org/W1668090144","https://openalex.org/W2504993638","https://openalex.org/W2083168956","https://openalex.org/W2980853820","https://openalex.org/W404373762","https://openalex.org/W2186004379","https://openalex.org/W2107427363","https://openalex.org/W2132764178","https://openalex.org/W2090788874"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4,29],"emerged":[5],"as":[6,147],"a":[7,132],"powerful":[8],"solution":[9,134],"for":[10,15,51,139],"meeting":[11],"the":[12,44,171,174,192,198,201],"growing":[13],"demands":[14],"connectivity,":[16],"reliability,":[17],"low":[18],"latency":[19],"and":[20,34,46,104,109,113,116,150,157,167,184,196],"operational":[21,124],"efficiency":[22],"in":[23,122],"advanced":[24,136],"networks.":[25],"However,":[26],"most":[27],"research":[28],"focused":[30],"on":[31,179],"theoretical":[32],"analysis":[33],"simulations,":[35],"with":[36,67,160],"limited":[37],"investigation":[38],"into":[39],"real-world":[40,93,186],"deployment.":[41],"To":[42,126],"bridge":[43],"gap":[45],"support":[47,154],"practical":[48],"DRL":[49,149],"deployment":[50,159],"network":[52],"management,":[53],"we":[54,130],"first":[55],"present":[56],"an":[57,180],"orchestration":[58],"framework":[59],"that":[60],"integrates":[61],"ETSI":[62],"Multi-access":[63],"Edge":[64],"Computing":[65],"(MEC)":[66],"Open":[68],"RAN,":[69],"enabling":[70],"seamless":[71],"adoption":[72],"of":[73,173,200],"DRL-based":[74],"strategies":[75],"across":[76,106],"different":[77],"time":[78,166],"scales":[79],"while":[80],"enhancing":[81],"agent":[82],"lifecycle":[83],"management.":[84],"We":[85],"then":[86],"identify":[87],"three":[88,193],"critical":[89],"challenges":[90,195],"hindering":[91],"DRL's":[92],"deployment,":[94],"including":[95],"asynchronous":[96],"requests":[97],"from":[98],"unpredictable":[99],"or":[100],"bursty":[101],"traffic,":[102,142],"adaptability":[103],"generalization":[105],"heterogeneous":[107,155],"topologies":[108],"evolving":[110],"service":[111,117,168],"demands,":[112],"prolonged":[114],"convergence":[115,165],"interruptions":[118],"due":[119],"to":[120,153,163],"exploration":[121],"live":[123],"environments.":[125],"address":[127],"these":[128],"challenges,":[129],"propose":[131],"three-fold":[133],"strategy:":[135],"time-series":[137],"integration":[138],"handling":[140],"asynchronized":[141],"flexible":[143],"architecture":[144,176],"design":[145],"such":[146],"multi-agent":[148],"incremental":[151],"learning":[152,162],"scenarios,":[156],"simulation-driven":[158],"transfer":[161],"reduce":[164],"disruptions.":[169],"Lastly,":[170],"feasibility":[172],"MEC-O-RAN":[175],"is":[177],"validated":[178],"urban-wide":[181],"testing":[182],"infrastructure,":[183],"two":[185],"use":[187],"cases":[188],"are":[189],"presented,":[190],"showcasing":[191],"identified":[194],"demonstrating":[197],"effectiveness":[199],"proposed":[202],"solutions.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-07-12T00:00:00"}