摘要
提出基于粗糙集的模糊神经网络流量预测算法。传统的流量控制技术,总是以网络资源当前使用情况对包进行处理,没有考虑流量预测问题,易造成流量控制滞后的情况。将基于粗糙集的模糊神经网络引入流量控制,利用其处理不确定性问题和自学习能力,进行流量预测,较好地解决这一问题。最后仿真分析了本方法的性能,证明方法的有效性。
A kind of network congestion forecast method based on rough fuzzy neural networks is proposed. The normal technology of load balancing, such as master-slave scheduler and threshold scheduler, always assign the task based on the present load of workstation. So, the resource utility is low and control of load balancing is lagged. The fuzzy neural network method presented can solve these limitations satisfactorily for its good capability of processing inaccurate information and self-learning. The results of simulations show that the FNN method is effective.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2006年第8期2101-2104,共4页
Journal of System Simulation
基金
江苏省博士后科研资助计划(0202003402)
南京理工大学青年学者基金(njsut06001)
南京理工大学科研发展基金(2005-2006)
关键词
分类决策
性能检测
网络故障诊断
拥塞预测
classificationdecision
performance detection
network troubleshooting
congestion forecast
