As a novel computing paradigm, vehicular edge computing (VEC) provides additional computing capacity to connected automated vehicles by deploying resources of computing and storage on base stations or roadside units. Vehicles migrate their tasks to VEC servers for execution through computation offloading (CO) to improve processing efficiency. However, the high-speed movement of vehicles causes handover among multiple VEC servers while raising the security issue of data sharing. In this paper, we design a mobility-aware CO and blockchain-based handover architecture to reduce the latency and improve the security of vehicular CO. A CO decision problem with models of mobility, CO, and blockchain-based handover is proposed to optimize the offloading decision of vehicles. Further, we transform this optimization into a Markov decision process (MDP) and construct a multi-agent deep reinforcement learning (MADRL) algorithm to solve it. The effectiveness and performance of the proposed method are verified by simulations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Mobility-Aware Computation Offloading and Blockchain-based Handover in Vehicular Edge Computing Networks


    Contributors:
    Lang, Ping (author) / Tian, Daxin (author) / Duan, Xuting (author) / Zhou, Jianshan (author)


    Publication date :

    2022-10-08


    Size :

    513368 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Cooperative Computation Offloading in Blockchain-Based Vehicular Edge Computing Networks

    Lang, Ping / Tian, Daxin / Duan, Xuting et al. | IEEE | 2022



    Blockchain-Based Secure Computation Offloading in Vehicular Networks

    Zheng, Xiao / Li, Mingchu / Chen, Yuanfang et al. | IEEE | 2021


    Mobility Aware Blockchain Enabled Offloading and Scheduling in Vehicular Fog Cloud Computing

    Lakhan, Abdullah / Ahmad, Muneer / Bilal, Muhammad et al. | IEEE | 2021