基于模糊神经网络的RTT智能预测算法  

RTT Intelligent Prediction Algorithm Based on Fuzzy Neural Network

作　　者：张莉[1] 邹宽胜[2] 

机构地区：[1]天津现代职业技术学院,天津300350 [2]江苏师范大学,江苏徐州221116

出　　处：《软件导刊》2013年第9期53-55,共3页Software Guide

基　　金：江苏省高校自然科学基金项目(13KJB520007)

摘　　要：在网络拥塞控制的重要参数中,RTT(Round trip time)尤为突出,因为它能对网络所发生的拥塞作出较早的反映。所以对RTT的精确预测程度,无论是对网络拥塞控制还是流量、带宽估计都很有意义。分析了RTT的特性,发现其有很强的高频噪声,因而采用低通滤波和MBP网络相结合的RTT预测策略。实验表明,即使在网络状况较忙的情况下,也能获得很好的预测结果。The important parameters of the network congestion control, RTT （Round trip time） is particularly prominent, because it can be caused by network congestion to the earlier reflect. Therefore, predicting RTT accurately has significance not only to network congestion control, but also to flow and bandwidth prediction. This paper analyses the characters of RTT, and finds that it has high frequency noise greatly. So that it adopts low-pass filtering combined with modified BP neural network as the intelligent predictive method. Experiments show that it gets pretty good results even in the poor network condition.

关 键 词：网络拥塞控制 往返延时 模糊神经网络 智能预测 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]