This paper considers the autonomous detecting and tracking task of the unmanned aerial vehicle (UAV) in the maritime environment. In the maritime UAV tracking system, due to the large size of the image computing-task and the shortage of UAV batteries and computational capability, the UAV needs to offload the computing-intensive task to the edge computing server (ECS) to reduce energy consumption and task latency. However, the task latency is still too long for the UAV tracking algorithm due to the large image size. We research the impact of image resolution on the computing task size and detection accuracy, and formulate an edge-aided UAV system with dynamic image resolution. With the constraint on task latency, we jointly optimize the image resolution, offloading rate, transmission power and local central processing unit (CPU) frequency to minimize energy consumption. Although the proposed problem is non-convex, we transform it into a convex optimization problem through decoupling and problem decomposition, and obtain an optimal offloading strategy. The numerical results show the energy efficiency of the proposed strategy by comparing it with the local first offloading strategy and the edge first offloading strategy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optimal Offloading of Computing-intensive Tasks for Edge-aided Maritime UAV Systems


    Contributors:
    Li, Huanran (author) / Wu, Shaohua (author) / Li, Dongqing (author) / Jiao, Jian (author) / Zhang, Ning (author) / Zhang, Qinyu (author)


    Publication date :

    2022-06-01


    Size :

    1337280 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Computing on Surface: A Multi-Task Multi-Access Offloading Scheme in Maritime Edge Networks

    Dai, Minghui / Dou, Chenglong / Wu, Yuan et al. | IEEE | 2024


    Multi-hop fronthaul offloading in learning-aided fog computing

    Kaneva, Kameliya / Aboutorab, Neda / Leu, George | IEEE | 2021


    SAFELY SCHEDULING OFFLOADING OF COMPUTING TASKS FOR AN AUTONOMOUS VEHICLE

    FARUQUE MOHAMMAD ABDULLAH AL / SAKR YASSER SHOUKRY AHMED / ODEMA MOHANAD MOHAMED ABDELMAGID ABDELKHALEK et al. | European Patent Office | 2024

    Free access