%0 Journal Article
%T ROUTING STRATEGY BASED ON MULTI-AGENT SYSTEMS AND NEURAL NETWORK<br>基于多Agent系统和神经网络的路由选择策略
%A DONG Jun
%A PAN Yun-He
%A <br>董军
%A 潘云鹤
%J 自动化学报
%D 2002
%I 
%X In mainland China, long distance telecommunications network's switch and link usage rates are only about 45% and 30%~40%, respectively. It is estimated that raising one percent of switch rate of the current network will result in revenue almost one billion RMB. In the paper, by analysing the demerit of routing schemes being used, a new intelligent routing strategy based on multi-agent systems and neural network forecasting is presented, including network model, routing procedure, and agent connotation depiction. Meanwhile, recurrent neural network forecasting is introduced. Simulation demonstrates it is outstanding by virtue of distribution and intelligence. Hence it provides an excellent way to improve switch rate and balance of network load.
%K Route selection
%K multi-agent systems
%K switch rate
%K load balancing
%K neural network forecasting<br>电信网
%K 多Agent系统
%K 神经网络
%K 路由选择策略
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=D27FF3EF5F7128BB&yid=C3ACC247184A22C1&vid=D3E34374A0D77D7F&iid=E158A972A605785F&sid=42D7028D961473F8&eid=D8AE57480552698F&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=9