首页> 外文期刊>American Journal of Operations Research >Neural-Based Routing Method for Alleviating Congestion in Complex Networks
【24h】

Neural-Based Routing Method for Alleviating Congestion in Complex Networks

机译:减轻复杂网络拥塞的基于神经的路由方法

获取原文
           

摘要

In this paper, we propose a new packet routing strategy that incorporates memory information for reducing congestion in communication networks. First, we study the conventional routing strategy which selects the paths for transmitting packets to destinations using the distance information and the dynamical information such as the number of accumulating packets at adjacent nodes. Then, we evaluate the effectiveness of this routing strategy for the scale-free networks. From results of numerical simulations, we conclude that this routing strategy is not effective when the density of the packets increases due to the impermeability of the communication network. To avoid this undesirable problem, we incorporate memory information to the routing strategy. By using memory information effectively, packets are spread into the communication networks, achieving a higher performance than conventional routing strategies for various network topologies, such as scale-free networks, small-world networks, and scale-free networks with community
机译:在本文中,我们提出了一种新的分组路由策略,该策略结合了内存信息以减少通信网络中的拥塞。首先,我们研究传统的路由策略,该策略使用距离信息和动态信息(例如,相邻节点上的累积数据包数量)来选择将数据包传输到目的地的路径。然后,我们评估了这种路由策略对无标度网络的有效性。从数值模拟的结果中,我们得出结论,当分组的密度由于通信网络的不可渗透性而增加时,这种路由策略无效。为避免此不良问题,我们将内存信息纳入了路由策略。通过有效地使用内存信息,数据包被散布到通信网络中,从而实现了比常规路由策略更高的性能,适用于各种网络拓扑,例如无标度网络,小型世界网络和具有社区的无标度网络。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号