一种基于匹配博弈的服务链协同映射方法

A Collaborative Mapping Method for Service Chain Based on Matching Game

针对软件定义网络(SDN)/网络功能虚拟化(NFV)环境下服务链映射难以兼顾效率与物理资源利用率的问题,该文提出一种基于匹配博弈的服务链协同映射方法。首先,以最大化网络资源效用为目标,建立服务链映射模型MUSCM;然后,分虚拟网络功能(VNF)部署和组链两个部分解决服务链映射问题,VNF部署部分,设计基于多对一匹配博弈理论的算法协同服务链和服务节点双方互相进行选择,有效提升了服务链的映射效率和物理资源的利用率,在此基础上,设计基于分段路由策略的算法实现各VNF实例间的流量牵引以完成VNF组链,有效降低了链路传输时延。实验结果表明,与经典算法相比,该算法在保证映射请求接受率的同时,有效降低了服务链的平均传输延时,提升了系统的物理资源利用率。

Considering that it is difficult to balance efficiency and resource utilization of Service Chain(SC)mapping problem in Software Defined Network(SDN)/Network Function Virtualization(NFV)environment,this paper proposes a collaborative mapping method for SC based on matching game.Firstly,it defines a SC mapping model named MUSCM to maximize the utility of network resources.Secondly,it divides the SC mapping problem into Virtual Network Function(VNF)deployment and connection parts.As for the VNF deployment part,an algorithm is designed to collaborate the selection of the SC and the service node based on many-to-one matching game,improving the mapping efficiency of SC and utilization of physical resource effectively.On the basis of it,an algorithm is designed based on segment routing strategy to accomplish the traffic steering between VNF instances to finish the VNF connection part,reducing the link transmission delay effectively.The experiment result shows that,compared with the classical algorithm,this algorithm ensures the mapping request received rate,and at the same time,it reduces the average transmission delay of the service chain and improves the physical resources utilization of the system effectively.