基于蚁群算法的SDN数据中心网络大象流调度研究

Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》

李宏慧 杨光 路海亮 付学良 申志军

Abstract： The traditional methods may cause network congestion and load imbalance when scheduling the elephant flows in data center networks. To deal with these isuses, this paper proposed scheme ACO-SDN, which is based on ACO (ant colony) algorithm in SDN(Software Defined Network) data center networks. It built an ILP（Integral Linear Programing）model according to the flow scheduling problem, with the object of minimize the maximum link utilization. Then, it employed ant colony algorithm to solve the ILP model through redefining its parameters and operations. The optimal route was obtained for of rerouting elephant flows. The experimental results show that, in comparisons with ECMP(Equal-Cost multi-path Routing) and GFF (Global First Fit) algorithms, ACO-SDN algorithm lowers down the maximum link utilization rate, and effectively improves the network bisection bandwidth of networks.

YES

 Hits 3217  Downloads 1740  Comment 0