摘要
目前,NOX、FloodLight等SDN控制器均提供了类似于传统路由器OSPF协议的最短路径转发算法,这些算法通过SDN控制器收集全局交换机静态参数从而进行路径计算,但并没有利用SDN系统的优势即获得运行时的动态信息来优化算法性能,在流量过大时传统算法容易导致网络拥堵。对SDN的路由算法进行研究,应用粒子群算法并利用SDN技术的特点对网络的负载均衡问题进行相关的优化。仿真实验表明与ECMP算法相比,提出的算法可以在一定程度提升网络的整体利用率,降低网络的时延和拥塞。
At present ,SDN controllers such as NOX and FloodLight provide the shortest path forwarding algorithm similar to the traditional router OSPF protocol .These algorithms collect the global parameters of the switch through the SDN controller ,but do not take advantage of the SDN system to obtain runtime dynamic information to optimize the perfor-mance of the algorithm ,traditional algorithms are prone to network congestion when traffic is too large .This paper mainly studies the routing algorithm of SDN ,proposed the application of particle swarm optimization algorithm ,combined with the characteristics of SDN technology to optimize the network load .The simulation results show that the proposed algorithm can improve the overall utilization of the network and reduce the congestion of the network to a certain extent .
出处
《国外电子测量技术》
2017年第10期23-26,共4页
Foreign Electronic Measurement Technology
