Wi-Fi网络移动边缘计算资源分配策略研究

Research on Resource Allocation Scheme for Mobile Edge Computing Based on Wi-Fi Networks

移动边缘计算(Mobile Edge Computing,MEC)在网络边缘提供计算服务,能够满足时延敏感型、计算密集型应用计算需求。Wi-Fi网络具有大带宽、低时延、分布广、安全性高等特点,相比蜂窝网络更能满足移动边缘计算的需求。针对基于802.11ax Wi-Fi网络下的计算任务卸载与资源分配问题,提出了基于坐标下降法与任务优先级的卸载与资源分配方案。首先将原始优化问题拆分为卸载决策子问题与资源分配子问题,其次在给定卸载策略的前提下根据任务优先级进行资源分配,同时基于坐标下降法对卸载策略进行迭代优化。仿真结果表明,所提方案能够在显著降低移动设备任务处理总能耗的同时,提高服务质量(Quality of Service,QoS)满意率,有效提高了基于Wi-Fi网络的MEC性能。

MEC(Mobile Edge Computing)can provide computing services at the edge of network,which can meet the processing requirements of delay-sensitive and computing-intensive applications.Wi-Fi networks have the features of large bandwidth,low delay,high security,and it is widely distributed.Thus,Wi-Fi networks can better meet the needs of mobile edge computing compared with cellular networks.Therefore,aiming at the problem of computing task offloading and resource allocation based on 802.11ax Wi-Fi networks,this paper proposes an offloading and resource allocation scheme based on coordinate descent method and task priority.First,the original optimization problem is divided into offloading decision subproblem and resource allocation sub-problem.Then,resources are allocated according to task priority when offloading decision is given,and the offloading decision is iteratively optimized based on coordinate descent method.Simulation results indicate that the proposed scheme can not only significantly reduce the total task processing energy consumption of mobile devices,but also improve the QoS satisfaction rate,and effectively improve the performance of MEC based on Wi-Fi networks.