{"id":"https://openalex.org/W4414270314","doi":"https://doi.org/10.1109/jiot.2025.3611003","title":"Dynamic Model Deployment, Batch Scheduling, and Resource Allocation in MLLM-Enabled Edge\u2013Cloud Networks: A Multiagent Two-Timescale DRL Approach","display_name":"Dynamic Model Deployment, Batch Scheduling, and Resource Allocation in MLLM-Enabled Edge\u2013Cloud Networks: A Multiagent Two-Timescale DRL Approach","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4414270314","doi":"https://doi.org/10.1109/jiot.2025.3611003"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2025.3611003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3611003","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5002941898","display_name":"Hualong Huang","orcid":"https://orcid.org/0000-0003-2176-3931"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hualong Huang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2176-3931","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050878172","display_name":"Yongkang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Du","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0008-5293-0652","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043425375","display_name":"Wenhan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Zhan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1851-7185","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102079217","display_name":"Hancong Duan","orcid":"https://orcid.org/0000-0002-7721-7422"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hancong Duan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-7721-7422","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067587036","display_name":"Kai Peng","orcid":"https://orcid.org/0000-0003-4809-2234"},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Peng","raw_affiliation_strings":["College of Engineering, Huaqiao University, Quanzhou, China","College of Engineering, Huaqiao University, Quanzhou, P.R.China"],"raw_orcid":"https://orcid.org/0000-0003-4809-2234","affiliations":[{"raw_affiliation_string":"College of Engineering, Huaqiao University, Quanzhou, China","institution_ids":["https://openalex.org/I119045251"]},{"raw_affiliation_string":"College of Engineering, Huaqiao University, Quanzhou, P.R.China","institution_ids":["https://openalex.org/I119045251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031364544","display_name":"Yamin Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yamin Cheng","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu, China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062262445","display_name":"Yalan Ye","orcid":"https://orcid.org/0000-0001-5974-1717"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalan Ye","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084729575","display_name":"Zitian Zhao","orcid":"https://orcid.org/0000-0001-8605-0938"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitian Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-8605-0938","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5002941898"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.3517,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85726785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":"23","first_page":"50818","last_page":"50835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9857000112533569,"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":0.9857000112533569,"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":0.98089998960495,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.920799970626831,"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/software-deployment","display_name":"Software deployment","score":0.8395000100135803},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6119999885559082},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5041999816894531},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.48030000925064087},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.4293999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8787000179290771},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8395000100135803},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6036999821662903},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.4293999969959259},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.39320001006126404},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C145062175","wikidata":"https://www.wikidata.org/wiki/Q5318947","display_name":"Dynamic bandwidth allocation","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26579999923706055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3611003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3611003","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2568803418","display_name":null,"funder_award_id":"U2333211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2017977879","https://openalex.org/W3010178570","https://openalex.org/W3094144275","https://openalex.org/W4286377419","https://openalex.org/W4294643302","https://openalex.org/W4316876954","https://openalex.org/W4385245566","https://openalex.org/W4386108500","https://openalex.org/W4387321091","https://openalex.org/W4390828922","https://openalex.org/W4392901652","https://openalex.org/W4393139888","https://openalex.org/W4394586114","https://openalex.org/W4399168608","https://openalex.org/W4399205883","https://openalex.org/W4399426597","https://openalex.org/W4400447774","https://openalex.org/W4400660342","https://openalex.org/W4400975133","https://openalex.org/W4401752634","https://openalex.org/W4401753387","https://openalex.org/W4402716477","https://openalex.org/W4403421327","https://openalex.org/W4403826595","https://openalex.org/W4404238050","https://openalex.org/W4404562740","https://openalex.org/W4404914599","https://openalex.org/W4405934565","https://openalex.org/W4410226386","https://openalex.org/W4410428120","https://openalex.org/W4412164080","https://openalex.org/W4412170838","https://openalex.org/W4412870994","https://openalex.org/W4412939588","https://openalex.org/W7084088851"],"related_works":[],"abstract_inverted_index":{"The":[0],"deployment":[1,48,95,105],"of":[2,39],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"on":[8],"resource-constrained":[9],"mobile":[10],"devices":[11],"poses":[12],"significant":[13],"challenges":[14],"due":[15],"to":[16,91],"their":[17],"high":[18],"computational":[19],"demands.":[20],"This":[21],"paper":[22],"introduces":[23],"a":[24,72],"novel":[25],"two-timescale":[26],"optimization":[27],"framework":[28],"for":[29,143],"efficient":[30],"MLLM":[31,134],"inference":[32],"in":[33,128],"Edge-Cloud":[34],"networks,":[35],"addressing":[36],"the":[37,121],"problem":[38],"multi-timescale":[40],"resource":[41,55,98],"management":[42],"by":[43],"jointly":[44],"optimizing":[45],"slow-timescale":[46,93],"MLLMs":[47,94],"decisions":[49],"and":[50,57,64,86,96,109,136],"fast-timescale":[51,97],"batch":[52],"scheduling,":[53],"GPU":[54],"allocation,":[56,99],"bandwidth":[58],"allocation":[59],"under":[60],"dynamic":[61,137],"network":[62,138],"conditions":[63],"spatiotemporal":[65],"request":[66],"heterogeneity.":[67],"Our":[68],"key":[69],"innovation":[70],"is":[71],"hierarchical":[73],"twin":[74],"delayed":[75],"deep":[76],"deterministic":[77],"policy":[78],"gradient":[79],"(HALTD3)":[80],"algorithm":[81,123],"that":[82,120],"integrates":[83],"attention":[84],"mechanisms":[85],"long":[87],"short-term":[88],"memory":[89],"networks":[90],"optimize":[92],"minimizing":[100],"weighted":[101],"system":[102,130],"costs":[103,131],"including":[104],"cost,":[106],"end-to-end":[107],"latency,":[108],"energy":[110],"consumption,":[111],"while":[112],"meeting":[113],"stringent":[114],"quality-of-service":[115],"requirements.":[116],"Extensive":[117],"experiments":[118],"demonstrate":[119],"HALTD3":[122],"substantially":[124],"outperforms":[125],"baseline":[126],"methods":[127],"reducing":[129],"across":[132],"diverse":[133],"workloads":[135],"scenarios,":[139],"validating":[140],"its":[141],"effectiveness":[142],"practical":[144],"edge-cloud":[145],"collaborative":[146],"inference.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-20T23:13:51.555489","created_date":"2025-10-10T00:00:00"}
