{"id":"https://openalex.org/W4394913539","doi":"https://doi.org/10.1145/3638782.3638825","title":"D2D communication resource allocation algorithm based on multi-agent reinforcement learning","display_name":"D2D communication resource allocation algorithm based on multi-agent reinforcement learning","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4394913539","doi":"https://doi.org/10.1145/3638782.3638825"},"language":"en","primary_location":{"id":"doi:10.1145/3638782.3638825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638782.3638825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 13th International Conference on Communication and Network Security","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060963494","display_name":"Taoshen Li","orcid":"https://orcid.org/0009-0005-9899-5214"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taoshen Li","raw_affiliation_strings":["Information Engineering, Nanning University, China"],"raw_orcid":"https://orcid.org/0009-0005-9899-5214","affiliations":[{"raw_affiliation_string":"Information Engineering, Nanning University, China","institution_ids":["https://openalex.org/I4210151929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5095769364","display_name":"Zhijun Qi","orcid":"https://orcid.org/0009-0000-1724-4624"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Qi","raw_affiliation_strings":["Computer, Electronics and Information, Guangxi University, China"],"raw_orcid":"https://orcid.org/0009-0000-1724-4624","affiliations":[{"raw_affiliation_string":"Computer, Electronics and Information, Guangxi University, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9775999784469604,"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":0.8194683790206909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7652472853660583},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.5639162659645081},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.48168954253196716},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4518342912197113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35902678966522217},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27599596977233887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8194683790206909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652472853660583},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5639162659645081},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48168954253196716},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4518342912197113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35902678966522217},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27599596977233887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638782.3638825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638782.3638825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 13th International Conference on Communication and Network Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2091503252","https://openalex.org/W2792817273","https://openalex.org/W2799349785","https://openalex.org/W2950522792","https://openalex.org/W2963000651","https://openalex.org/W3003545318","https://openalex.org/W3033715510","https://openalex.org/W3112254600","https://openalex.org/W3209841066","https://openalex.org/W3216595048","https://openalex.org/W4220827529","https://openalex.org/W4285282755"],"related_works":["https://openalex.org/W2923452570","https://openalex.org/W206598027","https://openalex.org/W2978610750","https://openalex.org/W2138260944","https://openalex.org/W2022931285","https://openalex.org/W1589966275","https://openalex.org/W2086872282","https://openalex.org/W2137789903","https://openalex.org/W2153007255","https://openalex.org/W2138781885"],"abstract_inverted_index":{"To":[0],"solve":[1],"the":[2,45,60,75,83,103,117,123,131],"interference":[3],"problem":[4,48,62,85],"of":[5,41,49,109,126,133],"device-to-device":[6],"(D2D)":[7],"communication":[8,51],"in":[9],"cellular":[10],"network,":[11],"a":[12,55,87],"distributed":[13,34],"resource":[14,35,46],"allocation":[15,36,47,61,108],"algorithm":[16,119],"based":[17],"on":[18],"simultaneous":[19],"wireless":[20],"information":[21],"and":[22,26,37,71,98,106,130,136,140],"power":[23,69],"transfer":[24],"technology":[25],"dual":[27],"deep":[28],"Q-network":[29],"is":[30,52,63,79],"proposed":[31,118],"to":[32,81],"achieve":[33],"maximize":[38],"energy":[39,124],"efficiency":[40,125],"D2D":[42,50,127,134],"links.":[43],"Firstly,":[44],"formulated":[53],"as":[54,86],"Markov":[56],"decision":[57],"process.":[58],"Secondly,":[59],"decomposed":[64],"into":[65],"two":[66],"sub":[67],"problems:":[68],"control":[70],"channel":[72],"allocation.":[73],"Then,":[74],"reinforcement":[76],"learning":[77,89,99],"technique":[78],"introduced":[80],"model":[82],"optimization":[84,104],"multi-agent":[88],"optimal":[90],"strategy":[91],"problem.":[92],"Finally,":[93],"by":[94],"continuously":[95],"iterative":[96],"updating":[97],"better":[100],"action":[101],"strategies,":[102],"goals":[105],"reasonable":[107],"resources":[110],"are":[111],"achieved.":[112],"Experimental":[113],"results":[114],"show":[115],"that":[116],"can":[120],"effectively":[121],"improve":[122],"link":[128],"layer":[129],"throughput":[132],"link,":[135],"has":[137],"certain":[138],"feasibility":[139],"effectiveness.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}