不确定网络环境中任务卸载和资源分配联合优化方法

Joint optimization method of task offloading and resourceallocation under uncertain wireless network

在不确定的无线网络环境中,由于任务到达、用户移动的随机性以及无线信道状态的时变性,导致出现不确定的任务云端排队时延、设备网络连接时间等网络环境特征,极大影响计算卸载效率和网络资源利用率。针对这一问题,建立了算网协同的动态任务卸载和资源联合分配模型,以最小化系统总能耗为目标,提出了基于随机模拟的任务卸载和算网资源联合分配多阶段随机规划优化算法(SS-MSSP),采用多阶段随机规划理论制定多阶段策略,并以后验算网资源分配的方式来追索补偿不确定网络环境的影响。仿真结果表明,在不确定的网络环境中,SS-MSSP算法保证了用户的计算时延需求,同时有效降低了系统能耗。

In an uncertain wireless network environment,the randomness of task arrival,user movement,and the time-varying nature of wireless channel states lead to uncertain network environment characteristics such as cloud queuing delay and device network connection time,which greatly affect the efficiency of computing offloading and network resource utilization.To address this issue,this paper establishes a dynamic task offloading and edge resource adaptive allocation model for computing and network coordination.A multi-stage stochastic programming optimization algorithm(SS-MSSP)for task offloading and joint resource allocation based on stochastic simulation was proposed with the goal of minimizing the total energy consumption of the system.The multi-stage stochastic programming theory was used to formulate multi-stage strategies,and the posteriori computing network resource allocation method was used to compensate for the impact of uncertain network environments.Simulation results show that in an uncertain network environment,the SS-MSSP algorithm ensures the user’s computing delay requirements while effectively reducing system energy consumption.