多种群粒子群的SDN控制器故障恢复算法  

SDN Controller Fault Recovery Algorithm Based on Multi-population Particle Swarm Optimization

作　　者：朱国晖 刘茹文 杨瑛 ZHU Guohui;LIU Ruwen;YANG Ying(School of Communication and Information Engineering,Xi’an University of Post&Telecommunications,Xi’an 710121,China)

机构地区：[1]西安邮电大学通信与信息工程学院,西安710121

出　　处：《计算机工程与应用》2022年第5期124-130,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(61371087)。

摘　　要：针对软件定义网络(software defined network,SDN)中控制器发生故障问题,提出了一种基于多种群粒子群算法的SDN控制器故障恢复策略。从其他正常工作的子控制器集合中挑选出能够容纳失控交换机负载的备份控制器集,将精英种群与子种群组成多种群粒子群,采用预选和交互机制演化出备份控制器的最优位置,以保证交换机与控制器之间的传播时延最小,完成失控交换机的迁移。实验结果表明,相比于现有的控制器故障恢复算法,该算法在恢复时间、控制器负载利用方面均有所提升。Aiming at the problem of controller fault recovery in software defined network(SDN),a controller fault recovery algorithm based on multi-population particle swarm optimization is proposed.Firstly,the backup controller set which can meet the capacity of the uncontrol switches is selected from other normal controller sets.Then the elite population and the sub populations are combined to form the multi-population particle swarm,the optimal position of backup controller is evolved by the mechanism of preselection and interaction in order that the propagation delay between switch and controller is minimum.Finally,the immigration of out of control switches is completed.The experimental results show that compared with the present algorithms,the proposed algorithm can improve the indicators such as recovery time and load utilization of controller.

关 键 词：软件定义网络 备份控制器 粒子群优化 故障恢复 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]