计算机科学 ›› 2009, Vol. 36 ›› Issue (7): 85-87.doi: 10.11896/j.issn.1002-137X.2009.07.020

• 计算机网络与信息安全 • 上一篇    下一篇

基于随机神经网络的多步网络时延预测模型

胡治国,张大陆,侯翠平,沈斌,朱安奇   

  1. (同济大学计算机科学与技术系 上海201804);(中国人民解放军65583部队 辽阳111000)
  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本课题受国家自然科学基金资助项目(90204010)资助。

Multi-step Network Delay Prediction Model Based on RNN

HU Zhi-guo,ZHANG Da-lu,HOU Cui-ping,SHEN Bin,ZHU An-qi   

  • Online:2018-11-16 Published:2018-11-16

摘要: 网络时延的动态变化反映了网络路径的负载特征,对时延的精确预测是实施网络拥塞控制、路由选择的重要依据,建立了基于随机神经网络的时延预测模型,该模型克服了传统时间序列预测方法受随机千扰因素影响大、模型结构辫识过程繁琐,以及传统神经网络预测方法易于陷入局部极值、偏离全局最优的缺点。仿真实验表明,在提前单步和多步的预测中该模型比AR模型、RBF神经网络预测算法的准确度更高。

关键词: 网络时延,RNN神经网络,预测

Abstract: Network delay is an important performance metric of IP network which reflects network path's workload characteristics. The precise prediction for network delay is an important basis on congestion control and route selection.A new multi-step prediction method was proposed for network delay prediction based on the random neural networks,this method overcomes the disadvantage traditional time-series method and neural network method. Compared with traditional RBF network and AR model,the experimental result indicated that the proposed model has better accuracy for single steps and multi steps prediction.

Key words: Network delay, Random neural network, Prediction

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!