针对目前软件定义网络中的多控制器负载失衡问题,提出一种交换机的动态迁移算法(dynamic switches migration algorithm,DSMA),将交换机与控制器的部署关系建模为0-1规划问题,通过使用免疫粒子群算法保证控制器负载均衡的同时兼顾了控制器和交换机之间的传输时延。仿真实验表明,与现有经典的就近迁移算法和利用率最低迁移算法相比,DSMA实现了较好的控制器负载均衡,减少了控制器PACKET_IN消息的响应时间,提高了系统反应速度,加权后的综合评价平均提升了25.3%。
Aiming at the load imbalance of multiple controllers in software defined networks,this paper proposed a dynamic switches migration algorithm( DSMA). By modeling the controller-switch mapping as 0-1 programming problem,this algorithm used the immune particle swarm algorithm to achieve the load balance of the controllers and ensured the transmission delay between controllers and switches at the same time. Simulation results show that,compared with the existed typical algorithms such as nearest migration algorithm and lowest utilization migration algorithm,DSMA achieves good load balancing of controllers,reduces the response time of the PACKET_IN messages,improves the system response speed and increases the weighted comprehensive evaluation meanly to 25. 3%.