基于改进PCNN算法的光网络RWA问题的研究

针对波分复用光网络在动态业务下的路由和波长分配问题,本文将一种改进的脉冲耦合神经网络(PCNN——Pulse Coupled Neural Networks)算法引入到光网络路由选择中,并将波长分配与分层图模型相结合,通过改变PCNN神经元的点火方式以及控制自动波的传播时间模拟路径代价,使得网络路由选择具有了PCNN的并行处理特性。结合波长分配算法进行仿真,结果表明,本算法与传统的最短路径算法相比,总能得到全局最优解且计算量小,降低了网络的呼叫阻塞率,提高了对网络资源的利用。

Study on RWA of Optical Network Based on Improved Pulse-Coupled Neural Network

Aiming at Routing and Wavelength Assignment(RWA) problem of WDM network under dynamic traffic flow, an intelligent algorithm based on improved pulse-coupled neural network(PCNN) is introduced into WDM routing, the wavelength selection makes use of layer model, through changing the firing aspect and using the auto-wave's transmitting time to simulate the route cost, the route selection of networks has the function of parallel proceeding, which is the basic characteristic of PCNN.Computer simulation shows tha...