{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:20:10Z","timestamp":1773994810206,"version":"3.50.1"},"reference-count":27,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276146"],"award-info":[{"award-number":["62276146"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2021J011112"],"award-info":[{"award-number":["2021J011112"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2023J011011"],"award-info":[{"award-number":["2023J011011"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2023J011016"],"award-info":[{"award-number":["2023J011016"]}]},{"name":"Scientific Research Startup Project of Putian University, Fujian Province, China","award":["2026036"],"award-info":[{"award-number":["2026036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Unmanned Aerial Vehicle (UAV)-assisted mobile edge computing is pivotal for the Space\u2013Air\u2013Ground\u2013Sea Integrated Network (SAGSIN) to support heterogeneous task offloading. However, the inherent resource constraints of UAVs limit their ability to support intensive and concurrent task processing in dynamic environments. In such complex scenarios, the dual requirements of discrete model partitioning and continuous bandwidth allocation make it difficult for traditional reinforcement learning algorithms to achieve optimal resource matching. Therefore, in this paper, we design a joint optimization framework based on Asynchronous Advantage Actor-Critic (A3C) and proximal policy optimization (PPO). Specifically, the model partitioning strategy is learned through PPO, which utilizes a clipped objective function to ensure training stability and generalization across complex Deep Neural Network (DNN) structures. Moreover, the framework leverages the asynchronous multi-threaded architecture of A3C to dynamically allocate bandwidth, effectively accommodating rapid fluctuations in terminal access. Finally, to prevent resource monopolization and ensure fairness, a weighted priority scheduling mechanism based on task urgency and computation time is introduced. Extensive simulations show that the proposed algorithm outperforms existing approaches in terms of task completion rate, task processing latency, and resource utilization under dynamic SAGSIN scenarios.<\/jats:p>","DOI":"10.3390\/e28030337","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:11:12Z","timestamp":1773828672000},"page":"337","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Model Partitioning and Bandwidth Allocation for UAV-Assisted Space\u2013Air\u2013Ground\u2013Sea Integrated Network: A Hybrid A3C-PPO Approach"],"prefix":"10.3390","volume":"28","author":[{"given":"Yuanmo","family":"Lin","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Putian University, Putian 351100, China"},{"name":"College of Communications Engineering, Army Engineering University of PLA, Nanjing 210000, China"}]},{"given":"Yuanyuan","family":"Han","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Putian University, Putian 351100, China"}]},{"given":"Minmin","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer and Data Science, Putian University, Putian 351100, China"}]},{"given":"Shaoyu","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computer and Data Science, Putian University, Putian 351100, China"}]},{"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Putian University, Putian 351100, China"}]},{"given":"Zhiyong","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Communications Engineering, Army Engineering University of PLA, Nanjing 210000, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"104041","DOI":"10.1016\/j.jnca.2024.104041","article-title":"A comprehensive systematic review on machine learning application in the 5G-RAN architecture: Issues, challenges, and future directions","volume":"233","author":"Talal","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6298","DOI":"10.1109\/TWC.2023.3241341","article-title":"Space-air-ground-sea integrated networks: Modeling and coverage analysis","volume":"22","author":"Xu","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1109\/COMST.2020.2997475","article-title":"Complementing IoT services through software defined networking and edge computing: A comprehensive survey","volume":"22","author":"Rafique","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"10947","DOI":"10.1007\/s10462-024-10947-4","article-title":"Cost optimization in edge computing: A survey","volume":"57","author":"Cao","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_5","first-page":"1","article-title":"An interference-aware and collision-free MAC protocol for underwater wireless sensor networks","volume":"21","author":"Zhu","year":"2025","journal-title":"ACM Trans. Sens. Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"29555","DOI":"10.1109\/JIOT.2025.3569270","article-title":"Energy-Efficient Trajectory Design and Unsupervised Clustering for UAV-Aided Fair Data Collections with Dense Ground Users","volume":"12","author":"Song","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"23509","DOI":"10.1109\/JIOT.2024.3385414","article-title":"An adaptive deployment scheme of unmanned aerial vehicles in dynamic vehicle networking for complete offloading","volume":"11","author":"Liao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1109\/OJCOMS.2024.3377706","article-title":"Meta reinforcement learning for UAV-assisted energy harvesting IoT devices in disaster-affected areas","volume":"5","author":"Dhuheir","year":"2024","journal-title":"IEEE Open J. Commun. Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/TITS.2025.3629117","article-title":"Deep Reinforcement Learning-Based Task Offloading with Collaborative Inference in UAV-Assisted Mobile Edge Computing Networks","volume":"27","author":"Zhai","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"111540","DOI":"10.1016\/j.comnet.2025.111540","article-title":"Joint optimization of data sensing and computing in the air-ground collaborative inference framework: A multi-agent hybrid-action DRL approach","volume":"270","author":"Fan","year":"2025","journal-title":"Comput. Netw."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"113548","DOI":"10.1016\/j.engappai.2025.113548","article-title":"Multiple quality-of-services optimization in space-air-ground integrated network: Centralized and decentralized deep reinforcement learning approaches","volume":"165","author":"Muy","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"111221","DOI":"10.1016\/j.comnet.2025.111221","article-title":"Deep reinforcement learning based computation offloading and resource allocation strategy for maritime internet of things","volume":"264","author":"Xu","year":"2025","journal-title":"Comput. Netw."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5810","DOI":"10.1109\/TCOMM.2024.3385923","article-title":"Performance analysis of multi-UAV aided cell-free radio access network with network-assisted full-duplex for URLLC","volume":"72","author":"Wan","year":"2024","journal-title":"IEEE Trans. Commun."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5179","DOI":"10.1109\/TCOMM.2024.3379417","article-title":"DDPG-based aerial secure data collection","volume":"72","author":"Lei","year":"2024","journal-title":"IEEE Trans. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1007\/s42405-025-00950-6","article-title":"Energy-aware adaptive obstacle avoidance based on meta-reinforcement learning with segmentation for UAV trajectory planning","volume":"27","author":"Archana","year":"2025","journal-title":"Int. J. Aeronaut. Space Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110686","DOI":"10.1016\/j.engappai.2025.110686","article-title":"Multiple aerial\/ground vehicles coordinated spraying using reinforcement learning","volume":"151","author":"Roshanian","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3385","DOI":"10.1109\/TNSM.2024.3364164","article-title":"AI-based radio resource management and trajectory design for IRS-UAV-assisted PD-NOMA communication","volume":"21","author":"Hariz","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhao, H., He, D., and Zhang, W. (2025). Secure communication and resource allocation in double-RIS cooperative-aided UAV-MEC networks. Drones, 9.","DOI":"10.3390\/drones9080587"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1109\/LCOMM.2024.3396500","article-title":"Maritime distributed computation offloading in space-air-ground-sea integrated networks","volume":"28","author":"Lin","year":"2024","journal-title":"IEEE Commun. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103616","DOI":"10.1016\/j.cja.2025.103616","article-title":"Joint optimization via deep reinforcement learning for secure-driven NOMA-UAV networks","volume":"38","author":"Deng","year":"2025","journal-title":"Chin. J. Aeronaut."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"110346","DOI":"10.1016\/j.sigpro.2025.110346","article-title":"Self-organized anti-jamming reinforcement learning for resource allocation in UAV-assisted networks","volume":"240","author":"Zhou","year":"2026","journal-title":"Signal Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"68710","DOI":"10.1109\/ACCESS.2025.3562102","article-title":"Optimizing Resource Allocation and Task Offloading in Multi-UAV MEC Networks","volume":"13","author":"Ahmed","year":"2025","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"23797","DOI":"10.1109\/TITS.2022.3205175","article-title":"Deep Reinforcement Learning for Computation and Communication Resource Allocation in Multiaccess MEC Assisted Railway IoT Networks","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TSC.2021.3116597","article-title":"DDPQN: An Efficient DNN Offloading Strategy in Local-Edge-Cloud Collaborative Environments","volume":"15","author":"Xue","year":"2022","journal-title":"IEEE Trans. Serv. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"20040","DOI":"10.1109\/JIOT.2024.3368216","article-title":"FedCD: A hybrid federated learning framework for efficient training with IoT devices","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.dcan.2018.10.003","article-title":"Deep Reinforcement Learning-Based Joint Task Offloading and Bandwidth Allocation for Multi-User Mobile Edge Computing","volume":"5","author":"Huang","year":"2019","journal-title":"Digit. Commun. Netw."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3561","DOI":"10.1109\/COMST.2025.3542467","article-title":"A Unifying View of OTFS and Its Many Variants","volume":"27","author":"Deng","year":"2025","journal-title":"IEEE Commun. Surv. Tutor."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/337\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T05:19:58Z","timestamp":1773983998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/337"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":27,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["e28030337"],"URL":"https:\/\/doi.org\/10.3390\/e28030337","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]}}}