【摘要】 路由选择是电信网的关键技术之一 ,其优劣直接影响着网络的接通率和负载平衡程度 .我国长途电信网的接通率只有 45 %左右 ,链路的利用率又仅为 30 %— 40 % .据介绍 ,若其接通率提高一个百分点 ,收益可达 10亿元 .随着业务量的飞速增长 ,路由选择问题日益突出 .文中在分析目前程控交换机所使用的路由选择方法的不足的基础上 ,提出基于多 Agent系统和神经网络预测的智能路由策略 ,介绍系统模型和选择方法 .它因良好的分布特性和智能决策能力而优于其它方法更多还原

【Abstract】 Routing being one of key issues of telecommunication management network influences the switch rate and load balancing of networks directly. In Chinese mainland, network switch and link usage rates is about 45% and 30%—40% respectively. It is said that raising one percent of switch rate of current telecommunications network will result in revenue almost one billion. The routing becomes more and more important as the telecommunications traffic’s increasing at full speed. In the paper, on the basic of demerit analysis of routing methods being used in switcher, a kind of intelligent routing strategy based on multi agent systems and neural network prediction is presented. Its model and method are introduced in detail.更多还原