| 摘要: |
| 针对车联网异构业务共存时卸载决策和计算资源分配不合理造成时延和能耗增加的问题，提出了一种多阶段异构业务任务卸载与计算资源联合分配(Multi-stage Heterogeneous Services Joint Task Offloading and Computation Resource Allocation，MHS-JTOCRA)算法。首先构建了超可靠低时延通信(Ultra-reliable and Low Latency Communications，URLLC)车辆与增强移动宽带(Enhanced Mobile Broadband，eMBB)车辆共存的移动边缘计算(Mobile Edge Computing，MEC)系统模型，在保证URLLC和eMBB业务服务质量(Quality of Service，QoS)的同时，通过考虑卸载所需的计算资源、时延和能耗，对遗传算法进行迭代求解，获得eMBB和URLLC业务的最优卸载决策和计算资源分配策略。仿真结果表明，所提算法与现有任务卸载和资源分配算法相比时延降低16.37%，能耗降低12.16%。 |
| 关键词: 车联网 eMBB-URLLC共存 任务卸载 计算资源分配 遗传算法 |
| DOI：10.20079/j.issn.1001-893x.231113003 |
|
| 基金项目: |
|
| Task Offloading and Computation Resource Allocation for Heterogeneous Services in Internet of Vehicles |
| FENG Jiao,BAI Ruobing,LI Peng,CHENG Fang,ZHANG Zhizhong |
| (1.School of Electronics&Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;2.Zhongguancun Pan-United Mobile Communication Technology Innovation and Application Research Institute,Beijing 100876,China) |
| Abstract: |
| To solve the problem of system delay and energy consumption increase caused by unreasonable offloading decision and computation resource allocation when heterogeneous services coexist in Internet of Vehicles(IoV),a multi-stage heterogeneous services joint task offloading and computation resource allocation(MHS-JTOCRA) algorithm is proposed.A mobile edge computing(MEC) system model is constructed for the coexistence of Ultra-reliable and Low Latency Communications(URLLC) vehicles and Enhanced Mobile Broadband(eMBB) vehicles.While ensuring the quality of service(QoS) of URLLC and eMBB services,the algorithm obtains the optimal offloading decision and computing resource allocation strategy for eMBB and URLLC services by considering the computational resources required for offloading,delay and energy consumption,iteratively solving the genetic algorithm.Simulation results show that the proposed algorithm reduces delay by 16.37% and energy consumption by 12.16% compared with existing task offloading and resource allocation algorithms. |
| Key words: Internet of Vehicles eMBB-URLLC coexistence task offloading computation resource allocation genetic algorithm |
