Digital Twin Assisted Task Offloading for Aerial Edge Computing and Networks

被引:104
作者
Li, Bin [1 ,2 ]
Liu, Yufeng [1 ]
Tan, Ling [1 ]
Pan, Heng [3 ,4 ]
Zhang, Yan [5 ,6 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Comp & Software, Nanjing 210044, Peoples R China
[2] Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
[3] Zhongyuan Univ Technol, Zhengzhou 450007, Peoples R China
[4] Henan Int Joint Lab Blockchain Data Sharing, Zhengzhou 450007, Peoples R China
[5] Univ Oslo, N-0315 Oslo, Norway
[6] Simula Metropolitan Ctr Digital Engn, N-0167 Oslo, Norway
基金
中国国家自然科学基金;
关键词
Task analysis; Autonomous aerial vehicles; Energy consumption; Digital twins; Trajectory; Servers; Resource management; Digital twin; unmanned aerial vehicle; mobile edge computing; user mobility; deep reinforcement learning; RESOURCE-ALLOCATION; COST; OPTIMIZATION;
D O I
10.1109/TVT.2022.3182647
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Considering the user mobility and unpredictable mobile edge computing (MEC) environments, this paper studies the intelligent task offloading problem in unmanned aerial vehicle (UAV)-enabled MEC with the assistance of digital twin (DT). We aim at minimizing the energy consumption of the entire MEC system by jointly optimizing mobile terminal users (MTUs) association, UAV trajectory, transmission power distribution and computation capacity allocation while respecting the constraints of mission maximum processing delays. Specifically, double deep Q-network (DDQN) algorithm stemming from deep reinforcement learning is first proposed to effectively solve the problem of MTUs association and UAV trajectory. Then, the closed-form expression is employed to handle the problem of transmission power distribution and the computation capacity allocation problem is further addressed via an iterative algorithm. Numerical results show that our proposed scheme is able to converge and significantly reduce the total energy consumption of the MEC system compared to the benchmark schemes.
引用
收藏
页码:10863 / 10877
页数:15
相关论文
共 39 条
[11]  
Huynh D. V., 2022, P IEEE INT C COMM IC, P1
[12]   Intelligent Offloading for NOMA-Assisted MEC via Dual Connectivity [J].
Li, Changxiang ;
Wang, Hong ;
Song, Rongfang .
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (04) :2802-2813
[13]  
Li J, 2018, IEEE INT CONF COMMUN, P798, DOI 10.1109/ICCChina.2018.8641189
[14]  
Li Y, 2021, 2021 IEEE Wireless Communications and Networking Conference (WCNC), P1
[15]   Path Planning for UAV-Mounted Mobile Edge Computing With Deep Reinforcement Learning [J].
Liu, Qian ;
Shi, Long ;
Sun, Linlin ;
Li, Jun ;
Ding, Ming ;
Shu, Feng .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (05) :5723-5728
[16]   Digital-Twin-Assisted Task Offloading Based on Edge Collaboration in the Digital Twin Edge Network [J].
Liu, Tong ;
Tang, Lun ;
Wang, Weili ;
Chen, Qianbin ;
Zeng, Xiaoping .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (02) :1427-1444
[17]   Communication-Efficient Federated Learning for Digital Twin Edge Networks in Industrial IoT [J].
Lu, Yunlong ;
Huang, Xiaohong ;
Zhang, Ke ;
Maharjan, Sabita ;
Zhang, Yan .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (08) :5709-5718
[18]   Low-Latency Federated Learning and Blockchain for Edge Association in Digital Twin Empowered 6G Networks [J].
Lu, Yunlong ;
Huang, Xiaohong ;
Zhang, Ke ;
Maharjan, Sabita ;
Zhang, Yan .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (07) :5098-5107
[19]  
Lv ZH, 2020, IEEE CONF COMPUT, P478, DOI 10.1109/INFOCOMWKSHPS50562.2020.9162853
[20]  
Molin Li, 2019, 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), P90, DOI 10.1109/PDCAT46702.2019.00028