MPLS网络加速梯度粒子群算法建立最佳LSP研究

MPLS network with the accelerating gradient particle swarm algorithm to establish the best LSP research

在MPLS网络中利用加速梯度粒子群算法对粒子速度的影响,通过对群体进行部分初始化保持群体的活性,减少了陷入局部最优的可能性,加速收敛到全局最优解,并在多条LSP中寻找出最优的LSP。仿真结果表明,该算法在MPLS网络模型中能降低网络阻塞率,优化网络资源利用率,有效减少了网络传输时延。

This article utilizes accelerating gradient of particle swarm optimization to effect the change of the particle velocity in the MPLS network. When groups information falls into the local optimum, by initializing partly group,this algorithm maintains the activity of the group, reduces the possibility of falling into local opti- mum, accelerates convergence to the global optimum solution and find out the optimal LSP from multiple LSP. The simulation results show that the algorithm reduces effectively network blocking rate and the trans- mission delay of the network, optimizes network resources utilization rate.