长相关业务量平均排队延迟的神经网络估计方法

摘要

从学者研究自然结构和科学数据的自相似性和分形性质,如网络流量数据等中,引入了一种估计多源排队系统中平均排队延迟的新方法.应用神经网络建模方法对自相似业务量进行预测并测定到达率和丢包率,以适应自相似流量模式的排队系统.%From many researches on observing self-similarity and fractals in natural structures and scientific database such as traffic data from networks,A novel approach for estimating average queuing delay in multiple source queuing systems is introduced.The approach relies on the modeling power of neural networks in predicting self-similar traffic patterns in order to determine the arrival rate and the packet latency of low loss,moderately loaded queuing systems accommodating such traffic patterns.