一种基于小波变换和FIR神经网络的广域网网络流量预测模型

田妮莉; 喻莉

doi:10.3724/SP.J.1146.2007.00451

一种基于小波变换和FIR神经网络的广域网网络流量预测模型

doi: 10.3724/SP.J.1146.2007.00451

田妮莉,
喻莉

基金项目:

国家自然科学基金(60502023)资助课题

计量
- 文章访问数: 3107
- HTML全文浏览量: 88
- PDF下载量: 839
- 被引次数: 0
出版历程
- 收稿日期: 2007-03-26
- 修回日期: 2007-07-31
- 刊出日期: 2008-10-19

A WAN Network Traffic Prediction Model Based on Wavelet Transform and FIR Neural Networks

Tian Ni-Li,
Yu Li

摘要

摘要: 该文提出了一种基于小波变换和FIR神经网络的广域网网络流量预测模型，首先采用小波分解把网络流量数据分解成小波系数和尺度系数，即高频系数和低频系数，将这些不同频率成分的系数单支重构为高频流量分量和低频流量分量，利用FIR神经网络对这些分量分别进行预测，将合成之后的结果作为原始网络流量的预测。实验结果表明：采用该模型对实际的广域网网络流量数据进行预测，不仅可以得到较快的收敛效果，而且预测性能比现有的小波神经网络和FIR神经网络要好得多。
- 流量预测 /
- 小波变换 /
- FIR神经网络(FIRNN)
Abstract: In this paper, a WAN network traffic prediction model based on wavelet transform and FIR neural networks is proposed. The model employs wavelet transform which decomposes the traffic into high frequency coefficients and low frequency coefficients , then these different frequency coefficients are reconstructed by single branch to the high frequency traffic parts and the low frequency traffic parts which are sent individually into different FIR neural networks for prediction. The synthesized outputs are the predicted results of the original network traffic. The experimental results with the real WAN network traffic show that the proposed model has much better prediction performance compared to the wavelet neural networks and the FIR neural networks.
- T /
- r

HTML全文

参考文献(1)

[1] Yang Yuekang and Lung Chung-Horng. The role of trafficforecasting in QoS routing-a case study of time-dependentrouting. ICC 2005, Seoul Korea, 16-20 May 2005, Vol.1:224-228. [2] Leland W E, Taqqu M S, and Willinger W, et al.. On theself-similar nature of Ethernet traffic (Extended Version)[J].IEEE/ACM Trans. on Networking.1994, 2(1):1-15 [3] 蔡弘, 陈惠民, 李衍达. 自相似业务模型通信网络突发业务建模的新方法. 通信学报, 1997, 18(11): 51-59. [4] 洪飞, 吴志美. 基于小波的多尺度网络流量预测模型. 计算机学报, 2006, 29(1): 166-170. [5] 雷霆, 余镇危. 一种网络流量预测的小波神经网络模型. 计算机应用, 2006, 26(3): 526-528. [6] Zhao Qigang, Fang Xuming, and Li Qunzhan, et al.. WNNbasedNGN traffic prediction. Proc. ISADS 2005, Chengdu,China, 4-8 April 2005: 230-234. [7] Wan E A. Finite impulse response neural networks withapplications in time series prediction. [Ph.D. dissertation],Dept. Elect. Eng., Stanford Univ., Stanford, CA, 1993. [8] 林雪纲，郑成兴，窦旻等. 基于FIR 神经网络的以太网网络流量预测. 计算机工程, 2006, 23(8): 124-130. [9] 谭晓玲，许勇，张凌等. 网络流量短期预测方法的研究与应用.计算机工程与设计, 2006, 27(8): 1341-1345. [10] Sarvotham S, Riedi R, and Baraniuk R. Connection-levelAnalysis and Modeling of Network Traffic. ACM SIGCOMMInternet Measurement Workshop, 2001: 1-5. [11] 丛锁, 韩良秀, 刘岩等. 基于离散小波变换的网络流量多重分形模型. 通信学报, 2003, 24(5): 43-48. [12] 王新. 自相似网络流量的建模与预测. [硕士论文], 清华大学,2003. [13] 飞思科技产品研发中心. 小波分析理论与MATLAB 7 实现.北京: 电子工业出版社, 2005: 238-258. [14] Wan E A. Temporal backpropagation for FIR neuralnetworks. In: Proc Int Joint Conf Neural Networks, SanDiego, 1990: 575-580.

施引文献

资源附件(0)

访问统计