SDN动态停滞超时时间优化算法

Dynamic timeout optimization algorithm in SDN

针对当软件定义网络(SDN)数据量高峰时,SDN交换机有限的流表项资源会对网络性能有很大限制这一问题,提出了一种动态停滞超时时间优化(DTO)算法。先用动态指数平滑(DES)算法估计出下一时间周期内网络中的新增流表项数量,而后依据SDN中的实际负载状况,采用动态参数对流表项的停滞超时时间进行动态优化调整。经Mininet仿真证明:优化算法能有效提高流表匹配率、流表资源利用率以及网络平均吞吐量,提升整体网络性能。

Aiming at the problem that at the peak of software defined network(SDN) data,the limited flow entry resources of SDN switches will have a great limitation on network performance,a dynamic timeout time optimization(DTO)algorithm is proposed. The algorithm estimates the number of new flow entry in the network in the next time period by dynamic exponential smoothing(DES)algorithm,at first.And then,dynamically optimize and adjust the stagnation time of the flow entry by dynamic parameters,according to the actual load status in the SDN.The simulation in Mininet shows that the optimization algorithm can effectively improve matching ratio of flow entry,the utilization of flow entry resources and the average network throughput, and improve the performance of the whole network.