一种基于IBPSO的SDN控制器放置优化方案

Optimization scheme for SDN controllers’ placement based on IBPSO

提出了改进离散粒子群优化(improved binary particle swarm optimization,IBPSO)算法用来解决控制器放置问题。该算法基于粒子群的全局最优和单个粒子的个体最优来决定粒子当前取值概率,消除粒子当前值对下一步迭代的影响,从而加快收敛速度,找到更优的最终结果。仿真结果表明,与离散粒子群优化(binary particle swarm optimization,BPSO)算法相比,由该算法得出的控制器放置方案在实现控制器负载均衡的同时,还可以显著降低控制器的数量。

This paper proposed an improved binary particle swarm optimization(IBPSO)algorithm to solve the controllers’placement problem.IBPSO algorithm determined the current value of particles based on both the global optimal and the individual optimal,thus weakened the influence of particle current value on the next iteration,and accelerated the convergence,which leaded to a better final result.The simulation results show that compared with the BPSO algorithm,the controllers’placement scheme obtained by this algorithm can significantly reduce the number of controllers while realizing the load balancing of the controller.