In this paper, we study a tracking service vehicular edge computing (VEC) network that provides computation offloading service for Intelligent vehicles, where computational tasks with different urgency and dependency are required to be completed efficiently within strict time constraints. We consider the actual scenario where the environmental parameters fluctuate randomly and their distributions are unknown, thus, a long-term scheduling policy optimization problem needs to be solved. For this motivation, we first define a queueing criterion to sort the subtasks into a scheduling queue, and then model a specific Markov decision process (MDP) according to the scheduling queue. Furthermore, we propose our vehicular task scheduling policy optimizing (VTSPO) algorithm based on the most advanced policy-based deep reinforcement learning (DRL). The experimental results compared with known value-based DRL algorithms verify the advantages of the proposed VTSPO algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dependency-Aware Vehicular Task Scheduling Policy for Tracking Service VEC Networks


    Contributors:
    Li, Chao (author) / Liu, Fagui (author) / Wang, Bin (author) / Chen, C. L. Philip (author) / Tang, Xuhao (author) / Jiang, Jun (author) / Liu, Jie (author)

    Published in:

    Publication date :

    2023-03-01


    Size :

    1619341 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Dependency-aware Task Scheduling and Cache Placement in Vehicular Networks

    Zhang, Lintao / Zhao, Caijin / Wang, Yuanyu et al. | IEEE | 2022




    Mobility and Deadline-Aware Task Scheduling Mechanism for Vehicular Edge Computing

    da Costa, Joahannes B. D. / de Souza, Allan M. / Meneguette, Rodolfo I. et al. | IEEE | 2023

    Free access

    Context-Aware Service Placement at the Edge in Vehicular Networks

    Zhang, Wanlu / Tao, Chenhui / Luo, Jingjing et al. | IEEE | 2023