{"id":"https://openalex.org/W4417282477","doi":"https://doi.org/10.1109/pimrc62392.2025.11274808","title":"Digital Twin-Based Reinforcement Learning for Beam Selection in Cell-Free Networks","display_name":"Digital Twin-Based Reinforcement Learning for Beam Selection in Cell-Free Networks","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4417282477","doi":"https://doi.org/10.1109/pimrc62392.2025.11274808"},"language":null,"primary_location":{"id":"doi:10.1109/pimrc62392.2025.11274808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100542726","display_name":"Yifeng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifeng Yang","raw_affiliation_strings":["Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396383","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-1527-5966"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439698","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0003-2663-4207"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042930332","display_name":"Wanli Ni","orcid":"https://orcid.org/0000-0003-0436-2685"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanli Ni","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056225611","display_name":"Yongming Huang","orcid":"https://orcid.org/0009-0009-2545-2875"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongming Huang","raw_affiliation_strings":["Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communication Research Laboratory,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100542726"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39356194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.8828999996185303,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.8828999996185303,"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/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.017000000923871994,"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/T11458","display_name":"Advanced Wireless Communication Technologies","score":0.015699999406933784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7580999732017517},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6507999897003174},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.545199990272522},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.5005999803543091},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.4724999964237213},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.31540000438690186},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3059000074863434}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7580999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253000140190125},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6507999897003174},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C168834538","wikidata":"https://www.wikidata.org/wiki/Q3705329","display_name":"Beam (structure)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C108921912","wikidata":"https://www.wikidata.org/wiki/Q7834639","display_name":"Transmission delay","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pimrc62392.2025.11274808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2035330915","https://openalex.org/W2157552453","https://openalex.org/W2286275639","https://openalex.org/W2944851425","https://openalex.org/W3209298344","https://openalex.org/W3212407382","https://openalex.org/W4243280356","https://openalex.org/W4286893914","https://openalex.org/W4323521196","https://openalex.org/W4393062393","https://openalex.org/W4396523201","https://openalex.org/W4396754388","https://openalex.org/W4402350254","https://openalex.org/W4405056282"],"related_works":[],"abstract_inverted_index":{"Cell-free":[0],"massive":[1],"multiple-input":[2],"multiple-output":[3],"(CF-mMIMO)":[4],"networks":[5,22],"improve":[6],"spectral":[7],"efficiency":[8],"via":[9],"coordinated":[10],"transmission":[11],"and":[12,37,49,78,105],"flexible":[13],"beam":[14,46],"selection.":[15],"However,":[16],"the":[17,30,60,92],"resource":[18],"allocation":[19],"in":[20,68],"such":[21,71],"presents":[23],"a":[24,45,84,115],"high-dimensional":[25],"optimization":[26],"challenge":[27],"due":[28],"to":[29,90,109,121],"distributed":[31],"architecture":[32],"with":[33],"multiple":[34],"access":[35],"points":[36],"antennas.":[38],"To":[39],"address":[40],"this,":[41],"we":[42,82],"first":[43],"formulate":[44],"selection":[47],"problem,":[48],"then":[50],"propose":[51],"an":[52],"efficient":[53],"Q-value":[54],"mixing":[55],"(QMIX)-based":[56],"algorithm.":[57],"Furthermore,":[58],"recognizing":[59],"inherent":[61],"limitations":[62],"of":[63],"deep":[64],"reinforcement":[65],"learning":[66],"(DRL)":[67],"practical":[69],"applications,":[70],"as":[72],"costly":[73],"training,":[74],"risky":[75],"exploration":[76],"phases,":[77],"suboptimal":[79],"convergence":[80,104],"speeds,":[81],"design":[83],"data-driven":[85],"digital":[86],"twin":[87],"(DT)":[88],"framework":[89],"optimize":[91],"DRL":[93],"training":[94],"phase.":[95],"Simulation":[96],"results":[97],"show":[98],"that":[99],"our":[100],"approach":[101],"achieves":[102],"accelerated":[103],"enhanced":[106],"stability":[107],"compared":[108],"conventional":[110],"methods.":[111],"DT-based":[112],"pre-training":[113],"establishes":[114],"robust":[116],"performance":[117],"lower":[118],"bound":[119],"prior":[120],"real-system":[122],"deployment.":[123]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-12T00:00:00"}