摘 要：基于云计算的车载网络是车辆终端与云中心之间分配计算任务的有效方式。为了进一步提高计算卸载效率，降低计算卸载的延迟，提出了一种基于移动边缘计算（MEC）的车载网络框架。研究了车辆到路边通信单元（V2I）和车辆到车辆（V2V）通信模式下的计算卸载效率。考虑任务计算的能耗与车辆的移动性，提出一种带预测传输的计算卸载方式，任务可以通过直接上传或是中继传输方式自适应地卸载到边缘服务器，从而提高任务传输效率。方案在满足计算任务时延约束的同时，可以大大提高传输效率，保证了在任务容忍延迟的情况下最小化卸载过程的总能耗。
关键词：移动边缘计算；车载网络；任务卸载；V2V
DOI:10.19850/j.cnki.2096-4706.2022.15.050
基金项目：甘肃省教育厅创新基金项目（2022A-215）；兰州石化职业技术大学 2021 年度校级教科研项目（KJ2021-09）
中图分类号：TN929.5 文献标识码：A 文章编号：2096-4706（2022）15-0195-04
Research on Vehicle Network Based on Mobile Edge Computing
SHAO Hua, NIU Jianhua, QUAN Yulong, JIANG Zhongtian
(Lanzhou Petrochemical University of Vocational Technology, Lanzhou 730060, China)
Abstract: Vehicle network based on cloud computing is an effective way to allocate computing tasks between vehicle terminal and cloud center. In order to further improve the efficiency of computing offloading and reduce the delay of computing offloading, this paper proposes a vehicle network framework based on Mobile Edge Computing (MEC). The computational offloading efficiency under Vehicle to Infrastructure (V2I) and Vehicle to Vehicle (V2V) communication modes are studied. Considering the energy consumption of task and vehicle mobility, a computing offloading method with predictive transmission is proposed. Tasks can be automatically offloaded to MEC server through direct upload or relay transmission mode, so as to improve the efficiency of task transmission. This scheme can greatly improve the transmission efficiency while meeting the time delay constraint of computing task. And it ensures to minimize the total energy consumption of offloading process under the condition of task tolerance delay.
Keywords: Mobile Edge Computing; vehicle network; task offloading; V2V
参考文献：
[1] 谢人超，廉晓飞，贾庆民，等 . 移动边缘计算卸载技术综述 [J]. 通信学报，2018，39（11）：138-155.
[2] 关丽华 . 基于雾计算边缘数据存储的缓存置换技术研究[J]. 山西电子技术，2017（4）：90-91+96.
[3] 田辉，范绍帅，吕昕晨，等 . 面向 5G 需求的移动边缘计算 [J]. 北京邮电大学学报，2017，40（2）：1-10.
[4] HUANG X M，YU R，KANG J W，et al. Exploring Mobile Edge Computing for 5G-Enabled Software Defined Vehicular Networks [J].IEEE Wireless Communications，2017，24（6）：55-63.
[5] SOLEYMANI S A，ABDULLAH A H，ZAREEI M，et al. A Secure Trust Model based on Fuzzy Logic in Vehicular Ad Hoc Networks with Fog Computing [J].IEEE Access，2017：15619-15629.
[6] WANG X J，WEI X，WANG L. A Deep Learning based Energy-efficient Computational Offloading Method in Internet of Vehicles [J].China Communications，2019，16（3）：81-91.
[7] LIU J Q，WAN J F，ZENG B，et al. A Scalable and QuickResponse Software Defined Vehicular Network Assisted by Mobile Edge Computing [J].IEEE Communications Magazine，2017，55（7）：94-100.
[8] CHIEN W C，WENG H Y，LAI C F. Q-learning based collaborative cache allocation in mobile edge computing [J].Future Generation Computer Systems，2020，102：603-610.
作者简介：邵华（1994.04—），女，汉族，甘肃兰州人，助教，硕士，主要研究方向：无线通信。