{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:42:25Z","timestamp":1773762145713,"version":"3.50.1"},"reference-count":38,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":75,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Communications"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The integration of artificial intelligence (AI) and the Internet of Things (IoT) has given rise to AIoT systems. However, the accelerated proliferation of AIoT ecosystems introduces substantial communication and networking difficulties. Mobile edge computing (MEC) has emerged as a promising solution to address time\u2010sensitive computational demands. This paper addresses the improvement of information freshness, a critical enabler for real\u2010time decision\u2010making in dynamic, resource\u2010constrained AIoT environments. We formulate the UAV\u2010assisted MEC system as a Markov decision process with the objective of minimizing the age of information (AoI). To this end, we propose an adaptive federated multi\u2010agent soft actor\u2010critic framework for resource scheduling. This framework leverages maximum entropy to enable robust exploration and incorporates an innovative adaptive federated learning mechanism by adopting a trainable network to predict the parameter matrix of federated learning. This enables federated learning to better promote knowledge sharing among multiple agents, thereby accelerating convergence and improving performance. Experimental results validate that our approach significantly outperforms state\u2010of\u2010the\u2010art reinforcement learning based algorithms in AoI minimization, stability enhancement, and task completion volume improvement, thereby advancing the safeguarding of communication and networking in AIoT\u00a0systems.<\/jats:p>","DOI":"10.1049\/cmu2.70146","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T13:28:58Z","timestamp":1773754138000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi\u2010Agent Soft Actor\u2010Critic Framework to Minimize Age of Information in UAV\u2010Assisted Networks"],"prefix":"10.1049","volume":"20","author":[{"given":"Tingshan","family":"Fan","sequence":"first","affiliation":[{"name":"School of Computer Science and Communication Engineering Northeastern University at Qinhuangdao Hebei China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2603-4626","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering Northeastern University at Qinhuangdao Hebei China"},{"name":"Hebei Key Laboratory of Marine Perception Network and Data Processing Hebei China"}]},{"given":"Yujie","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering Northeastern University at Qinhuangdao Hebei China"}]},{"given":"Ying","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering Northeastern University at Qinhuangdao Hebei China"}]},{"given":"Guorui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering Northeastern University at Qinhuangdao Hebei China"},{"name":"Hebei Key Laboratory of Marine Perception Network and Data Processing Hebei China"}]}],"member":"265","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"issue":"4","key":"e_1_2_12_2_1","doi-asserted-by":"crossref","first-page":"2409","DOI":"10.1109\/TCOMM.2020.2969666","article-title":"Enhance Latency\u2010Constrained Computation in MEC Networks Using Uplink NOMA","volume":"68","author":"Ye Y.","year":"2020","journal-title":"IEEE Transactions on Communications"},{"issue":"1","key":"e_1_2_12_3_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/TCCN.2020.3027695","article-title":"Multi\u2010Agent Deep Reinforcement Learning\u2010Based Trajectory Planning for Multi\u2010UAV Assisted Mobile Edge Computing","volume":"7","author":"Wang L.","year":"2020","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"key":"e_1_2_12_4_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2024.110469","article-title":"Multi\u2010Agent Deep Reinforcement Learning for Trajectory Planning in UAVs\u2010Assisted Mobile Edge Computing With Heterogeneous Requirements","volume":"248","author":"Fan C.","year":"2024","journal-title":"Computer Networks"},{"issue":"1","key":"e_1_2_12_5_1","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s11276-023-03492-5","article-title":"Minimizing Age of Information in Multi\u2010UAV\u2010Assisted IOT Networks: A Graph Theoretical Approach","volume":"30","author":"Rahimi O.","year":"2024","journal-title":"Wireless Networks"},{"issue":"1","key":"e_1_2_12_6_1","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1109\/TWC.2023.3278460","article-title":"Minimizing the AOI in Resource\u2010Constrained Multi\u2010Source Relaying Systems: Dynamic and Learning\u2010Based Scheduling","volume":"23","author":"Zakeri A.","year":"2024","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"4","key":"e_1_2_12_7_1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/TMC.2023.3267656","article-title":"Tradeoff Between Age of Information and Operation Time for UAV Sensing Over Multi\u2010Cell Cellular Networks","volume":"23","author":"Zhan C.","year":"2024","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"8","key":"e_1_2_12_8_1","doi-asserted-by":"crossref","first-page":"7944","DOI":"10.1109\/TVT.2019.2917890","article-title":"Computation Offloading and Resource Allocation for Cloud Assisted Mobile Edge Computing in Vehicular Networks","volume":"68","author":"Zhao J.","year":"2019","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"2","key":"e_1_2_12_9_1","doi-asserted-by":"crossref","first-page":"3121","DOI":"10.1109\/JIOT.2023.3294535","article-title":"Modeling on Resource Allocation for Age\u2010Sensitive Mobile Edge Computing Using Federated Multi\u2010Agent Reinforcement Learning","volume":"11","author":"Wang C.","year":"2023","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_2_12_10_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"1998"},{"key":"e_1_2_12_11_1","unstructured":"T. P.Lillicrap J. J.Hunt A.Pritzel et\u00a0al. \u201cContinuous Control With Deep Reinforcement Learning \u201dpreprint arXiv September 9 2015 https:\/\/doi.org\/10.48550\/arXiv.1509.02971."},{"key":"e_1_2_12_12_1","first-page":"6379","article-title":"Multi\u2010Agent Actor\u2010Critic for Mixed Cooperative\u2010Competitive Environments","volume":"30","author":"Lowe R.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"11","key":"e_1_2_12_13_1","doi-asserted-by":"crossref","first-page":"2606","DOI":"10.1109\/JSAC.2017.2760186","article-title":"Optimal Schedule of Mobile Edge Computing for Internet of Things Using Partial Information","volume":"35","author":"Lyu X.","year":"2017","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"4","key":"e_1_2_12_14_1","doi-asserted-by":"crossref","first-page":"3538","DOI":"10.1109\/TVT.2020.2970551","article-title":"Modeling and Analysis of the Uplink Local Delay in MEC\u2010Based VANETs","volume":"69","author":"Wu Y.","year":"2020","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"e_1_2_12_15_1","first-page":"73","volume-title":"International Conference on Mobile Networks and Management","author":"Lai H.","year":"2021"},{"issue":"2","key":"e_1_2_12_16_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/TCCN.2018.2809722","article-title":"Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks","volume":"4","author":"Wang S.","year":"2018","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"key":"e_1_2_12_17_1","first-page":"3184","volume-title":"ICC 2022\u2010IEEE International Conference on Communications","author":"Xu J.","year":"2022"},{"issue":"5","key":"e_1_2_12_18_1","doi-asserted-by":"crossref","first-page":"2698","DOI":"10.1109\/TCOMM.2023.3251353","article-title":"Augmented Deep Reinforcement Learning for Online Energy Minimization of Wireless Powered Mobile Edge Computing","volume":"71","author":"Chen X.","year":"2023","journal-title":"IEEE Transactions on Communications"},{"issue":"2","key":"e_1_2_12_19_1","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1109\/JIOT.2021.3091142","article-title":"Deep Reinforcement Learning for Energy\u2010Efficient Computation Offloading in Mobile\u2010Edge Computing","volume":"9","author":"Zhou H.","year":"2021","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_2_12_20_1","doi-asserted-by":"crossref","unstructured":"Y.Zhao J.Wang andB.Li \u201cA Deep Reinforcement Learning Approach to Online Microservice Deployment in Mobile Edge Computing \u201d inInternational Conference on Service\u2010Oriented Computing(Springer 2023) 127\u2013142.","DOI":"10.1007\/978-3-031-48424-7_10"},{"key":"e_1_2_12_21_1","doi-asserted-by":"crossref","unstructured":"L.\u2010T.Hsieh H.Liu Y.Guo andR.Gazda \u201cQuality of Service Optimization in Mobile Edge Computing Networks via Deep Reinforcement Learning \u201d inInternational Conference on Wireless Algorithms Systems and Applications(Springer 2020) 145\u2013157.","DOI":"10.1007\/978-3-030-59016-1_13"},{"issue":"12","key":"e_1_2_12_22_1","doi-asserted-by":"crossref","first-page":"6353","DOI":"10.1109\/TCOMM.2018.2866572","article-title":"Learning for Computation Offloading in Mobile Edge Computing","volume":"66","author":"Dinh T. Q.","year":"2018","journal-title":"IEEE Transactions on Communications"},{"issue":"5","key":"e_1_2_12_23_1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/MCOM.2019.1800971","article-title":"Computation Offloading in Multi\u2010Access Edge Computing Using a Deep Sequential Model Based on Reinforcement Learning","volume":"57","author":"Wang J.","year":"2019","journal-title":"IEEE Communications Magazine"},{"key":"e_1_2_12_24_1","doi-asserted-by":"crossref","unstructured":"L.Wang P.Huang K.Wang et\u00a0al. \u201cRL\u2010Based User Association and Resource Allocation for Multi\u2010UAV Enabled MEC \u201d in2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC)(IEEE 2019) 741\u2013746.","DOI":"10.1109\/IWCMC.2019.8766458"},{"key":"e_1_2_12_25_1","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.eng.2021.11.002","article-title":"MEC\u2010Empowered Non\u2010Terrestrial Network for 6G Wide\u2010Area Time\u2010Sensitive Internet of Things","volume":"8","author":"Liu C.","year":"2022","journal-title":"Engineering"},{"issue":"1","key":"e_1_2_12_26_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13638-020-01861-8","article-title":"Collaborative Offloading for UAV\u2010Enabled Time\u2010Sensitive MEC Networks","volume":"2021","author":"Li W.\u2010T.","year":"2021","journal-title":"EURASIP Journal on Wireless Communications and Networking"},{"issue":"5","key":"e_1_2_12_27_1","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.3390\/en16052486","article-title":"Federated\u2010Learning\u2010Based Energy\u2010Efficient Load Balancing for UAV\u2010Enabled MEC System in Vehicular Networks","volume":"16","author":"Shin A.","year":"2023","journal-title":"Energies"},{"key":"e_1_2_12_28_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2021.108439","article-title":"Computation Offloading Over Multi\u2010UAV MEC network: A Distributed Deep Reinforcement Learning Approach","volume":"199","author":"Wei D.","year":"2021","journal-title":"Computer Networks"},{"key":"e_1_2_12_29_1","doi-asserted-by":"crossref","unstructured":"Z.Zhu S.Wan P.Fan andK. B.Letaief \u201cAn Edge Federated Marl Approach for Timeliness Maintenance in MEC Collaboration \u201d in2021 IEEE International Conference on Communications Workshops (ICC Workshops)(IEEE 2021) 1\u20136.","DOI":"10.1109\/ICCWorkshops50388.2021.9473729"},{"issue":"1","key":"e_1_2_12_30_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/TCCN.2020.3027695","article-title":"Multi\u2010agent Deep Reinforcement Learning\u2010Based Trajectory Planning for Multi\u2010UAV Assisted Mobile Edge Computing","volume":"7","author":"Wang L.","year":"2020","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"issue":"1","key":"e_1_2_12_31_1","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/JSAC.2020.3036962","article-title":"Multi\u2010Agent Reinforcement Learning Based Resource Management in MEC\u2010and UAV\u2010Assisted Vehicular Networks","volume":"39","author":"Peng H.","year":"2020","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"12","key":"e_1_2_12_32_1","doi-asserted-by":"crossref","first-page":"9827","DOI":"10.1109\/JIOT.2020.3021006","article-title":"Federated Learning in the Sky: Aerial\u2010Ground Air Quality Sensing Framework With UAV Swarms","volume":"8","author":"Liu Y.","year":"2020","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_2_12_33_1","doi-asserted-by":"crossref","unstructured":"T.Zeng O.Semiari M.Mozaffari M.Chen W.Saad andM.Bennis \u201cFederated Learning in the Sky: Joint Power Allocation and Scheduling With UAV Swarms \u201d inIEEE International Conference on Communications (ICC)(IEEE 2020) 1\u20136.","DOI":"10.1109\/ICC40277.2020.9148776"},{"issue":"8","key":"e_1_2_12_34_1","doi-asserted-by":"crossref","first-page":"5140","DOI":"10.1109\/TITS.2021.3056341","article-title":"Towards Federated Learning in UAV\u2010Enabled Internet of Vehicles: A Multi\u2010Dimensional Contract\u2010Matching Approach","volume":"22","author":"Lim W. Y. B.","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"e_1_2_12_35_1","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/JBHI.2022.3157725","article-title":"Privacy\u2010Preserving Federated Learning for Internet of Medical Things Under Edge Computing","volume":"27","author":"Wang R.","year":"2022","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"2","key":"e_1_2_12_36_1","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1109\/MVT.2015.2411191","article-title":"Unmanned Aircraft Systems: Air\u2010Ground Channel Characterization for Future Applications","volume":"10","author":"Matolak D. W.","year":"2015","journal-title":"IEEE Vehicular Technology Magazine"},{"key":"e_1_2_12_37_1","unstructured":"T.Haarnoja A.Zhou K.Hartikainen et\u00a0al. \u201cSoft Actor\u2010Critic Algorithms and Applications \u201dpreprint arXiv December 13 2018 https:\/\/doi.org\/10.48550\/arXiv.1812.05905."},{"issue":"2","key":"e_1_2_12_38_1","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1109\/JIOT.2021.3078514","article-title":"Federated Multiagent Actor\u2010Critic Learning for Age Sensitive Mobile\u2010Edge Computing","volume":"9","author":"Zhu Z.","year":"2021","journal-title":"IEEE Internet of Things Journal"},{"issue":"7","key":"e_1_2_12_39_1","doi-asserted-by":"crossref","first-page":"4925","DOI":"10.1109\/TII.2020.3028963","article-title":"Deep Reinforcement Learning\u2010Based Dynamic Resource Management for Mobile Edge Computing in Industrial Internet of Things","volume":"17","author":"Chen Y.","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"}],"container-title":["IET Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70146","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cmu2.70146","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T13:29:04Z","timestamp":1773754144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cmu2.70146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/cmu2.70146"],"URL":"https:\/\/doi.org\/10.1049\/cmu2.70146","archive":["Portico"],"relation":{},"ISSN":["1751-8628","1751-8636"],"issn-type":[{"value":"1751-8628","type":"print"},{"value":"1751-8636","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-12-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70146"}}