软件定义网络中基于优先级的在线流调度策略

Online Traffic Scheduling Strategy Based on Priority in Software Defined Network

为了保证服务质量(quality of service,QoS),进入网络中的数据流可被赋予不同的优先级。在未来到达流请求信息未到达的情况下,进行在线优先级流调度,以最大化网络吞吐量是一项挑战。基于网络带宽资源、请求流的优先级和带宽需求的约束研究了软件定义网络(software defined networking,SDN)中的在线流请求调度策略。首先,提出了流路由成本和利润的概念,并创新性地设计了一个考虑边际成本的模型来描述链路资源和路由路径的使用成本。然后,将优先级流请求调度问题刻画为混合整数线性规划模型(mixed integer linear programming,MILP),提出在线优先级流调度算法(online priority traffic scheduling algorithm,OPTSA)来求解,最后分析了OPTSA的竞争比。仿真结果显示,与基准算法相比,所提出的算法可以确保网络负载均衡,同时有效提高网络的累积带宽和吞吐量。

In order to ensure the quality of service(QoS),the data flow entering the network is often given different priorities.It is challenging to schedule priority flows online to maximize network throughput without knowing the information of future arrival flow requests.The scheduling strategy of online flow requests in software defined networks(SDN)based on the constraints of network bandwidth resources,the priority of traffic requests,and bandwidth requirements was studied.Firstly,the concepts of flow routing cost and profit were proposed,and a cost model was designed to describe the cost of link resources and routing paths.Then,the priority flow request scheduling problem was characterized as a mixed integer linear programming(MILP)model,and an online priority traffic scheduling algorithm(OPTSA)was proposed to solve it.Finally,the competitive ratio of OPTSA was analyzed.Simulation results show that,compared with the benchmark algorithm,the proposed algorithm can effectively improve the cumulative bandwidth and throughput as well as ensuring the network load balancing.