基于SMDP模型的车路协同任务智能卸载算法  

Intelligent Offloading Algorithm for Road Collaborative TasksBased on SMDP Model

作　　者：李晓辉[1] 苏家楠 吕思婷 张鹏[1] LI Xiaohui;SU Jianan;LYU Siting;ZHANG Peng(School of Teleommunications Engineering,Xidian University,Xi'an 710071,China;Guangzhou Institute of Technology,Xidian University,Guangzhou 510555,China)

机构地区：[1]西安电子科技大学通信工程学院,西安710071 [2]西安电子科技大学广州研究院,广州510555

出　　处：《北京邮电大学学报》2023年第2期15-21,共7页Journal of Beijing University of Posts and Telecommunications

摘　　要：在车路协同系统中,车辆的高机动性会使边缘节点难以控制计算时延。对此,提出了基于半马尔可夫过程的任务卸载策略,定义了道路服务节点的优先级队列、状态空间、行为空间、系统收益和转移概率,用于构建任务等待队列模型。通过在服务节点覆盖范围内增加车载任务的完成率提高了整个系统的收益。此外,使用贝尔曼方程进行迭代,使系统的状态空间达到最优。仿真实验结果表明,所提的任务卸载策略可有效提高车路协同系统的整体收益。To solve the difficulties of delay control for the edge computing node caused by the the high mobility of vehicles in the vehicle-road coordination system,a task unloading strategy based on the semi-Markov decision process is proposed.First,the state space,action space,system reward,and transfer probability of the road service node are defined to model the task wait for the queue.Then,the overall benefit is improved by increasing the vehicle task completion rate within the coverage of the service node.Finally,the Bellman equation is used to iterate to make the state space reach the optimal system.The simulation results show that the task offloading decision of the algorithm can effectively improve the overall benefit of the vehicle-road collaboration system.

关 键 词：边缘计算 车路协同 任务卸载 半马尔可夫决策过程 

分 类 号：TN915[电子电信—通信与信息系统]