{"id":"https://openalex.org/W7160931162","doi":"https://doi.org/10.48550/arxiv.2605.10443","title":"HiRL: Hierarchical Reinforcement Learning for Coordinated Resource Management in Heterogeneous Edge Computing","display_name":"HiRL: Hierarchical Reinforcement Learning for Coordinated Resource Management in Heterogeneous Edge Computing","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160931162","doi":"https://doi.org/10.48550/arxiv.2605.10443"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101423335","display_name":"Jianyong Zhu","orcid":"https://orcid.org/0000-0002-6580-9818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jianyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135937166","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0003-4339-3441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135961529","display_name":"Juan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Juan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054549656","display_name":"Fangda Guo","orcid":"https://orcid.org/0000-0003-2401-6499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Fangda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015993565","display_name":"Albert Y. Zomaya","orcid":"https://orcid.org/0000-0002-3090-1059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zomaya, Albert Y.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135962730","display_name":"Renyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Renyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.5956000089645386,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.5956000089645386,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.17499999701976776,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.08630000054836273,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7936000227928162},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.6866999864578247},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.515500009059906},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4650000035762787},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.45750001072883606},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.451200008392334},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.4465999901294708},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.3953999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7936000227928162},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7049999833106995},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.6866999864578247},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.45750001072883606},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3953999876976013},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C123757187","wikidata":"https://www.wikidata.org/wiki/Q9195957","display_name":"Network dynamics","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.2639999985694885},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C147203929","wikidata":"https://www.wikidata.org/wiki/Q574814","display_name":"Discrete event simulation","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Edge":[0],"computing":[1],"faces":[2],"unprecedented":[3],"resource":[4,61,111,125,206],"orchestration":[5,62,207],"challenges":[6],"from":[7],"multi-dimensional":[8],"heterogeneity":[9],"across":[10],"device":[11,138],"architectures,":[12],"diverse":[13],"task":[14,29,68,88,169],"requirements":[15],"in":[16,208],"CPU-intensive,":[17],"GPU-intensive,":[18],"I/O-intensive,":[19],"and":[20,46,67,86,116,145,165],"dynamic":[21],"network":[22],"conditions.":[23,175],"The":[24],"edge":[25,210],"environments":[26],"demand":[27],"real-time":[28],"processing":[30],"within":[31],"strict":[32],"energy":[33,47,182],"budgets,":[34],"yet":[35],"conventional":[36],"approaches":[37,200],"struggle":[38],"with":[39,100,113,158],"mixed":[40],"continuous-discrete":[41],"optimization":[42,199],"while":[43,191],"meeting":[44],"deadline":[45],"constraints.":[48,126],"This":[49],"paper":[50],"presents":[51],"HiRL,":[52],"a":[53,97,107],"hierarchical":[54],"reinforcement":[55],"learning":[56],"framework":[57,132],"that":[58,152],"decomposes":[59],"complex":[60],"into":[63],"coordinated":[64],"power":[65,75],"control":[66],"allocation":[69],"decisions.":[70],"Our":[71],"approach":[72],"separates":[73],"continuous":[74],"management":[76],"using":[77,90],"the":[78,131],"Twin":[79],"Delayed":[80],"Deep":[81,92],"Deterministic":[82],"Policy":[83],"Gradient":[84],"(TD3)":[85],"discrete":[87],"placement":[89],"Double":[91],"Q-Network":[93],"(DDQN),":[94],"unified":[95],"through":[96],"coordination":[98],"engine":[99],"five-dimensional":[101],"queue":[102,140],"state":[103],"representation.":[104],"We":[105],"propose":[106],"heterogeneous":[108,209],"assessment":[109],"of":[110],"compatibility":[112],"deadline-oriented":[114],"prioritization":[115],"failure-penalized":[117],"adaptive":[118],"sampling":[119],"to":[120,163,177,186],"enhance":[121],"decision":[122],"quality":[123],"under":[124,172,188,201],"To":[127],"improve":[128],"practical":[129],"applicability,":[130],"models":[133],"comprehensive":[134],"system":[135],"dynamics":[136],"including":[137],"mobility,":[139],"congestion":[141],"patterns,":[142],"infrastructure":[143],"heterogeneity,":[144],"priority-sensitive":[146],"scheduling":[147],"demands.":[148],"Experimental":[149],"results":[150],"show":[151],"HiRL":[153,180],"achieves":[154],"effective":[155,205],"latency-energy":[156],"trade-offs":[157],"28%":[159],"latency":[160,195],"reduction":[161],"compared":[162],"Single-DDQN":[164],"maintains":[166],"nearly":[167],"100%":[168],"completion":[170],"rates":[171],"all":[173],"load":[174,190],"Compared":[176],"baseline":[178],"algorithms,":[179],"reduces":[181],"consumption":[183],"by":[184],"up":[185],"51%":[187],"low":[189],"achieving":[192],"24%":[193],"better":[194],"performance":[196],"than":[197],"static":[198],"high":[202],"load,":[203],"establishing":[204],"environments.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}