{"id":"https://openalex.org/W3127116426","doi":"https://doi.org/10.1109/twc.2021.3053319","title":"Accelerating Deep Reinforcement Learning With the Aid of Partial Model: Energy-Efficient Predictive Video Streaming","display_name":"Accelerating Deep Reinforcement Learning With the Aid of Partial Model: Energy-Efficient Predictive Video Streaming","publication_year":2021,"publication_date":"2021-01-28","ids":{"openalex":"https://openalex.org/W3127116426","doi":"https://doi.org/10.1109/twc.2021.3053319","mag":"3127116426"},"language":"en","primary_location":{"id":"doi:10.1109/twc.2021.3053319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2021.3053319","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Transactions on Wireless Communications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.soton.ac.uk/446613/1/final_manuscript.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407401","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0002-0619-1480"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dong Liu","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002903652","display_name":"Jianyu Zhao","orcid":"https://orcid.org/0000-0001-8519-6177"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Zhao","raw_affiliation_strings":["School of Electronics and Information Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082950698","display_name":"Chenyang Yang","orcid":"https://orcid.org/0000-0003-0058-0765"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Yang","raw_affiliation_strings":["School of Electronics and Information Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091122305","display_name":"Lajos Hanzo","orcid":"https://orcid.org/0000-0002-2636-5214"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lajos Hanzo","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100407401"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":1.0682,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.78444836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"6","first_page":"3734","last_page":"3748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9994000196456909,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9994000196456909,"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/T12238","display_name":"Green IT and Sustainability","score":0.9987999796867371,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8713826537132263},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8188256025314331},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5557253360748291},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5051234364509583},{"id":"https://openalex.org/keywords/base-station","display_name":"Base station","score":0.4807988703250885},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4348662495613098},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.41724228858947754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4159081280231476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3322314918041229},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17142727971076965},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.10525819659233093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8713826537132263},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8188256025314331},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5557253360748291},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5051234364509583},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.4807988703250885},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4348662495613098},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.41724228858947754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4159081280231476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3322314918041229},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17142727971076965},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.10525819659233093},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/twc.2021.3053319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2021.3053319","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Transactions on Wireless Communications","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:446613","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/446613/1/final_manuscript.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:eprints.soton.ac.uk:446613","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/446613/1/final_manuscript.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1032414495","display_name":"Converged Optical and Wireless Access Networks (COALESCE)","funder_award_id":"EP/P003990/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1972339859","display_name":null,"funder_award_id":"EP/P034284/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2422336959","display_name":null,"funder_award_id":"EP/P003990/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3583385501","display_name":"Cooperative backhaul aided next-generation digital subscriber loops","funder_award_id":"EP/N004558/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3964311364","display_name":null,"funder_award_id":"EP/N004558/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4532737952","display_name":null,"funder_award_id":"COALESCE","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5855793388","display_name":null,"funder_award_id":"Global Challenges Research Fund","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5991684347","display_name":"New Air Interface Techniques for Future Massive Machine-Type Communications","funder_award_id":"EP/P034284/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G797825634","display_name":null,"funder_award_id":"61731002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8719353587","display_name":null,"funder_award_id":"EP/P0","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3127116426.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1777890474","https://openalex.org/W2112170521","https://openalex.org/W2121863487","https://openalex.org/W2123117904","https://openalex.org/W2145339207","https://openalex.org/W2170157685","https://openalex.org/W2296520111","https://openalex.org/W2328010661","https://openalex.org/W2554984891","https://openalex.org/W2595800070","https://openalex.org/W2784465508","https://openalex.org/W2787938642","https://openalex.org/W2791838888","https://openalex.org/W2898035736","https://openalex.org/W2900935108","https://openalex.org/W2919115771","https://openalex.org/W2919677675","https://openalex.org/W2925458104","https://openalex.org/W2955026632","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2968782695","https://openalex.org/W2980574135","https://openalex.org/W3010275351","https://openalex.org/W3106096591","https://openalex.org/W3127116426","https://openalex.org/W4214717370","https://openalex.org/W6684921986","https://openalex.org/W6729507393","https://openalex.org/W6747790125","https://openalex.org/W6748839928","https://openalex.org/W6775256272"],"related_works":["https://openalex.org/W1626977535","https://openalex.org/W2145363145","https://openalex.org/W2963728120","https://openalex.org/W4386148312","https://openalex.org/W2891146212","https://openalex.org/W3117278457","https://openalex.org/W3213537191","https://openalex.org/W4319083788","https://openalex.org/W4287868411","https://openalex.org/W3212442854"],"abstract_inverted_index":{"Predictive":[0],"power":[1,70,85],"allocation":[2,71,86],"is":[3,18,194,235],"conceived":[4],"for":[5,60,228],"energy-efficient":[6],"video":[7,32,40],"streaming":[8,33],"over":[9,29],"mobile":[10],"networks":[11],"using":[12],"deep":[13,54],"reinforcement":[14],"learning.":[15],"The":[16,226],"goal":[17],"to":[19,53,67,134,189],"minimize":[20],"the":[21,36,45,62,84,89,92,105,119,123,127,145,150,155,160,165,176,185,190,204,208,215,219,230],"accumulated":[22],"energy":[23],"consumption":[24],"of":[25,159,167,210,232],"each":[26],"base":[27,128],"station":[28],"a":[30,136],"complete":[31],"session":[34],"under":[35],"constraint":[37],"that":[38,73,109,184,193],"avoids":[39],"playback":[41,142],"interruptions.":[42],"To":[43,139],"handle":[44],"continuous":[46],"state":[47,108],"and":[48,81,99,107,126,130,148,172,202],"action":[49,106],"spaces,":[50],"we":[51,117,153],"resort":[52],"deterministic":[55],"policy":[56,94,192,206],"gradient":[57],"(DDPG)":[58],"algorithm":[59],"solving":[61],"formulated":[63],"problem.":[64],"In":[65],"contrast":[66],"previous":[68],"predictive":[69],"policies":[72,187],"first":[74],"predict":[75],"future":[76],"information":[77],"with":[78],"historical":[79],"data":[80],"then":[82],"optimize":[83],"based":[87,196],"on":[88,112,197],"predicted":[90],"information,":[91],"proposed":[93,186],"operates":[95],"in":[96,207],"an":[97],"on-line":[98],"end-to-end":[100],"manner.":[101],"By":[102,213],"judiciously":[103],"designing":[104],"only":[110],"depend":[111],"slowly-varying":[113],"average":[114],"channel":[115,200],"gains,":[116],"reduce":[118],"signaling":[120],"overhead":[121],"between":[122],"edge":[124],"server":[125],"stations,":[129],"make":[131],"it":[132],"easier":[133],"learn":[135],"good":[137],"policy.":[138],"further":[140],"avoid":[141],"interruption":[143],"throughout":[144],"learning":[146],"process":[147],"improve":[149],"convergence":[151,220],"speed,":[152],"exploit":[154],"partially":[156,216],"known":[157,217],"model":[158],"system":[161],"dynamics":[162],"by":[163],"integrating":[164],"concepts":[166],"safety":[168],"layer,":[169],"post-decision":[170],"state,":[171],"virtual":[173],"experiences":[174],"into":[175],"basic":[177],"DDPG":[178],"algorithm.":[179],"Our":[180],"simulation":[181],"results":[182,231],"show":[183],"converge":[188],"optimal":[191],"derived":[195],"perfect":[198],"large-scale":[199],"prediction":[201,211],"outperform":[203],"first-predict-then-optimize":[205],"presence":[209],"errors.":[212],"harnessing":[214],"model,":[218],"speed":[221],"can":[222],"be":[223],"dramatically":[224],"improved.":[225],"code":[227],"reproducing":[229],"this":[233],"article":[234],"available":[236],"at":[237],"https://github.com/fluidy/twc2020.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}