一种新的基于混沌神经网络的动态路由选择算法

A new dynamic routing algorithm based on chaotic neural networks

针对通信网的路由选择问题,提出了一种动态路由选择的混沌神经网络实现方法。所提出的此方法具有许多优良特性,即暂态混沌特性和平稳收敛特性,能有效地避免传统Hopfield神经网络极易陷入局部极值的缺陷。它通过短暂的倒分叉过程,能很快进入稳定收敛状态。实验证明了本算法能实时、有效地实现通信网的路由选择,并且当通信网中的业务量发生变化时,算法能自动调整最短路径和负载平衡之间的关系。

A dynamic routing algorithm based on chaotic neural network is proposed to solve the routing problem in communication network. The proposed neural networks have many merits which are transient chaos and stable convergence etc. so as to overcome the drawbacks of easily getting stuck in local minim in conventional Hopfield neural networks. It can reach a stable convergent state after shortly reversed bifurcations. Simulations are also shown that the proposed algorithm is both efficient and effective in the routing selection, meanwhile the algorithm can adjust the balance between the shortest path and the least load requirements according to the link load status of the network.