{"id":"https://openalex.org/W3160306825","doi":"https://doi.org/10.1109/jsac.2021.3078498","title":"Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation","display_name":"Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation","publication_year":2021,"publication_date":"2021-05-10","ids":{"openalex":"https://openalex.org/W3160306825","doi":"https://doi.org/10.1109/jsac.2021.3078498","mag":"3160306825"},"language":"en","primary_location":{"id":"doi:10.1109/jsac.2021.3078498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2021.3078498","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","raw_type":"journal-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/A5006416547","display_name":"Zhouyou Gu","orcid":"https://orcid.org/0000-0001-9457-1135"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhouyou Gu","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079772530","display_name":"Changyang She","orcid":"https://orcid.org/0000-0003-0193-9784"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Changyang She","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003076132","display_name":"Wibowo Hardjawana","orcid":"https://orcid.org/0000-0001-6775-8682"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wibowo Hardjawana","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017921830","display_name":"Simon Lumb","orcid":null},"institutions":[{"id":"https://openalex.org/I40900055","display_name":"Telstra (Australia)","ror":"https://ror.org/04g047260","country_code":"AU","type":"company","lineage":["https://openalex.org/I40900055"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon Lumb","raw_affiliation_strings":["Telstra Corporation Ltd., Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Telstra Corporation Ltd., Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I40900055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044852763","display_name":"David McKechnie","orcid":null},"institutions":[{"id":"https://openalex.org/I40900055","display_name":"Telstra (Australia)","ror":"https://ror.org/04g047260","country_code":"AU","type":"company","lineage":["https://openalex.org/I40900055"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David McKechnie","raw_affiliation_strings":["Telstra Corporation Ltd., Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Telstra Corporation Ltd., Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I40900055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062811803","display_name":"Todd Essery","orcid":null},"institutions":[{"id":"https://openalex.org/I40900055","display_name":"Telstra (Australia)","ror":"https://ror.org/04g047260","country_code":"AU","type":"company","lineage":["https://openalex.org/I40900055"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Todd Essery","raw_affiliation_strings":["Telstra Corporation Ltd., Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Telstra Corporation Ltd., Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I40900055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043371405","display_name":"Branka Vucetic","orcid":"https://orcid.org/0000-0002-2700-2001"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Branka Vucetic","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006416547"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":6.6031,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97439586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"39","issue":"7","first_page":"2014","last_page":"2028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T11158","display_name":"Wireless Networks and Protocols","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8644847273826599},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8003329038619995},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6608259081840515},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6483204364776611},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6178236603736877},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5181923508644104},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47274717688560486},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.45005863904953003},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.448869526386261},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4126574993133545},{"id":"https://openalex.org/keywords/network-scheduler","display_name":"Network scheduler","score":0.41264528036117554},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.3815998435020447},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.30077409744262695},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2698950171470642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2644655704498291},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.230057954788208},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08971789479255676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644847273826599},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8003329038619995},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6608259081840515},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6483204364776611},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6178236603736877},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5181923508644104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47274717688560486},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.45005863904953003},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.448869526386261},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4126574993133545},{"id":"https://openalex.org/C163099246","wikidata":"https://www.wikidata.org/wiki/Q1978975","display_name":"Network scheduler","level":5,"score":0.41264528036117554},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.3815998435020447},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.30077409744262695},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2698950171470642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2644655704498291},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.230057954788208},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08971789479255676},{"id":"https://openalex.org/C108921912","wikidata":"https://www.wikidata.org/wiki/Q7834639","display_name":"Transmission delay","level":3,"score":0.0},{"id":"https://openalex.org/C180026317","wikidata":"https://www.wikidata.org/wiki/Q5000645","display_name":"Burst switching","level":4,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jsac.2021.3078498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2021.3078498","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G809942236","display_name":null,"funder_award_id":"DE150101704","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8281838290","display_name":null,"funder_award_id":"FL160100032","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W595252221","https://openalex.org/W1777239053","https://openalex.org/W1988622909","https://openalex.org/W2036533317","https://openalex.org/W2103581981","https://openalex.org/W2121863487","https://openalex.org/W2137898377","https://openalex.org/W2140385023","https://openalex.org/W2145339207","https://openalex.org/W2158698208","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2287724167","https://openalex.org/W2322852727","https://openalex.org/W2543381794","https://openalex.org/W2623491082","https://openalex.org/W2624731731","https://openalex.org/W2626444157","https://openalex.org/W2785518025","https://openalex.org/W2817158724","https://openalex.org/W2890389408","https://openalex.org/W2897442451","https://openalex.org/W2900764181","https://openalex.org/W2915644299","https://openalex.org/W2950892788","https://openalex.org/W2952685986","https://openalex.org/W2954543879","https://openalex.org/W2957938917","https://openalex.org/W2963077778","https://openalex.org/W2963250023","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964121960","https://openalex.org/W2970971581","https://openalex.org/W2971598376","https://openalex.org/W2979918265","https://openalex.org/W2996568029","https://openalex.org/W3008026851","https://openalex.org/W3028125283","https://openalex.org/W3031371304","https://openalex.org/W3040922689","https://openalex.org/W3101231502","https://openalex.org/W4295312788","https://openalex.org/W4366344170","https://openalex.org/W6638088447","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6700752644","https://openalex.org/W6739193204","https://openalex.org/W6766978945","https://openalex.org/W6781734511"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W2115248066","https://openalex.org/W4235045732","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,85,119,168],"develop":[4,169],"a":[5,30,55,63,87,101,121],"knowledge-assisted":[6,122],"deep":[7,47],"reinforcement":[8],"learning":[9],"(DRL)":[10],"algorithm":[11],"to":[12,38,99,189],"design":[13,120,132],"wireless":[14,95],"schedulers":[15,219],"in":[16,72,79,105,247],"the":[17,26,109,114,130,136,139,141,146,154,158,162,180,186,191,207,243],"fifth-generation":[18],"(5G)":[19],"cellular":[20],"networks":[21],"with":[22,230],"time-sensitive":[23],"traffic.":[24],"Since":[25],"scheduling":[27,39,143],"policy":[28,49],"is":[29],"deterministic":[31,48],"mapping":[32],"from":[33,94],"channel":[34],"and":[35,68,112,145,161,175,183,196,213,242],"queue":[36],"states":[37],"actions,":[40],"it":[41],"can":[42],"be":[43,70],"optimized":[44],"by":[45,153],"using":[46],"gradient":[50],"(DDPG).":[51],"We":[52],"show":[53,202,228],"that":[54,125,203,229],"straightforward":[56],"implementation":[57],"of":[58,116,129,138,148,157,164,210],"DDPG":[59,123,211],"converges":[60,246],"slowly,":[61],"has":[62],"poor":[64],"quality-of-service":[65],"(QoS)":[66],"performance,":[67],"cannot":[69],"implemented":[71],"real-world":[73,198],"5G":[74],"systems,":[75],"which":[76],"are":[77,97],"non-stationary":[78,197],"general.":[80],"To":[81,107],"address":[82],"these":[83],"issues,":[84],"propose":[86],"theoretical":[88,92],"DRL":[89],"framework,":[90],"where":[91,177],"models":[93],"communications":[96],"used":[98],"formulate":[100],"Markov":[102],"decision":[103],"process":[104],"DRL.":[106],"reduce":[108],"convergence":[110,208],"time":[111,209],"improve":[113],"QoS":[115,216,238],"each":[117,149],"user,":[118],"(K-DDPG)":[124],"exploits":[126],"expert":[127],"knowledge":[128,137],"scheduler":[131,181,187],"problem,":[133],"such":[134],"as":[135],"QoS,":[140],"target":[142],"policy,":[144],"importance":[147],"training":[150,174],"sample,":[151],"determined":[152],"approximation":[155],"error":[156],"value":[159],"function":[160],"number":[163],"packet":[165,224],"losses.":[166],"Furthermore,":[167],"an":[170],"architecture":[171],"for":[172],"online":[173,188,244],"inference,":[176],"K-DDPG":[178],"initializes":[179],"off-line":[182,194,231],"then":[184],"fine-tunes":[185],"handle":[190],"mismatch":[192],"between":[193],"simulations":[195],"systems.":[199],"Simulation":[200],"results":[201,227],"our":[204,233],"approach":[205,234],"reduces":[206],"significantly":[212],"achieves":[214,235],"better":[215,236],"than":[217,239],"existing":[218],"(reducing":[220],"30%":[221],"~":[222],"50%":[223],"losses).":[225],"Experimental":[226],"initialization,":[232],"initial":[237],"random":[240],"initialization":[241],"fine-tuning":[245],"few":[248],"minutes.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
