摘要
在数据中心网络中,多路径广泛存在,而传统的基于ECMP的流量调度方法容易造成大流碰撞问题,因此提出一种基于SDN的数据中心网络动态流量调度方法。利用SDN集中控制,具有全局视图的优点,对网络中的大象流进行调度。首先使用s Flow协议收集网络信息,然后基于多商品流问题对大象流的路径选择进行建模,最后使用粒子群算法求得全局最优解。仿真实验结果表明,与ECMP算法相比,本文提出的算法能够提高网络的利用率,获得更高的对分带宽。
In the data center network , multipath is widespread , but the traditional traffic scheduling method based on ECMP is likely to cause flow collision problem , therefore a new dynamic traffic scheduling method based on SDN is proposed .SDN has the advantages of centralized control , and global view of the network , so, it is used to schedule the elephant flow in network .In the scheme, firstly, the sFlow protocols is used to collect network information .Secondly the elephant flow path selection is modelled according to the multi-commodity flow problem.Last, we are trying to solve it by the particle swarm optimization to get the global optimal solution.Finally, the simulation results show that , the proposed algorithm can improve network utilization , achieve higher bisection bandwidth compared with the ECMP algorithm .
出处
《计算机与现代化》
2016年第7期80-86,共7页
Computer and Modernization
基金
国家自然科学基金资助项目(61202350)
作者简介
庄怀东(1989-),男,安徽宿州人,南京航空航天大学计算机科学与技术学院硕士研究生,研究方向:软件定义网络;
杜庆伟(1974-),男,河南郑州人,副教授,硕士生导师,博士,研究方向:计算机网络。