移动边缘计算中基于Stackelberg模型的分布式定价与计算卸载

Stackelberg Model Based Distributed Pricing and Computation Offloading in Mobile Edge Computing

移动边缘计算(Mobile Edge Computing, MEC)作为一种新颖的计算范式,通过将计算任务从移动设备卸载到物理上临近的网络边缘,为移动设备提供低延迟和灵活的计算与通信服务。然而,由于边缘服务器和移动设备通常属于不同的主体,它们之间的利益冲突给MEC系统带来了很大的挑战。因此,为多边缘服务器多移动设备的MEC系统设计一种定价和计算卸载方案,最大化边缘服务器的效用并优化移动设备的体验质量至关重要。考虑到多边缘服务器多移动设备之间复杂的相互作用,采用多领导者多追随者Stackelberg模型来分析它们之间的相互作用。其中,边缘服务器作为领导者为其计算资源设定价格,移动设备作为追随者根据边缘服务器的定价来调整卸载策略。在Stackelberg模型的基础上,提出了一种基于次梯度法的分布式迭代算法,该算法可以有效收敛到Stackelberg均衡。仿真实验结果表明,所提方案能够在提高边缘服务器效用的同时保证移动设备的体验质量。

As a novel computing paradigm,mobile edge computing(MEC)provides low latency and flexible computing and communication services for mobile devices by offloading computing tasks from mobile devices to the physically proximal network edge.However,because edge servers and mobile devices often belong to different parties,the conflicts of interest between them present a great challenge for MEC systems.Therefore,it is important to design a pricing and computing offloading scheme for MEC systems with multiple edge servers and mobile devices to maximize the utility of edge servers and optimize the quality of experience for mobile devices.Considering the complex interaction between multi-edge servers and mobile devices,the multi-leader and multi-follower Stackelberg model is used to analyze the interaction between them.The edge server acts as the leader to set the price for its computing resources,and the mobile device as the follower adjusts the offloading strategy according to the pricing of the edge server.Based on the Stackelberg model,a distributed iterative algorithm based on subgradient method is proposed,which can effectively converge to Stackelberg equilibrium.Simulation results show that the proposed scheme can improve the utility of edge server and guarantee the experience quality of mobile devices.