基于Morlet-SVR和ARIMA组合模型的网络流量预测

doi:10.13190/j.jbupt.2016.02.011

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (2): 53-57.doi: 10.13190/j.jbupt.2016.02.011

基于Morlet-SVR和ARIMA组合模型的网络流量预测

赵建龙¹, 曲桦^1,2, 赵季红^2,3, 戴慧珺²

1. 西安交通大学软件学院, 西安 710049;
2. 西安交通大学电子与信息工程学院, 西安 710049;
3. 西安邮电大学通信与信息工程学院, 西安 710061

收稿日期:2015-11-17 出版日期:2016-04-28 发布日期:2016-04-28
作者简介:赵建龙(1992-),男,博士生,E-mail:z.jl199235@stu.xjtu.edu.cn;曲桦(1961-),男,教授,博士生导师.
基金资助:
国家自然科学基金项目（61371087）；国家高技术研究发展计划（863计划）项目（2015AA015702）

A Comprehensive Forecasting Model for Network Traffic Based on Morlet-SVR and ARIMA

ZHAO Jian-long¹, QU Hua^1,2, ZHAO Ji-hong^2,3, DAI Hui-jun²

1. School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
2. School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
3. School of Communication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710061, China

Received:2015-11-17 Online:2016-04-28 Published:2016-04-28

摘要/Abstract

摘要：

针对网络流量的非线性和多维度动力学特性，结合小波多尺度分析的能力，提出了基于Morlet小波核函数的支持向量机回归算法（Morlet-SVR）和自回归积分滑动平均模型（ARIMA）的组合模型预测网络流量.采用Morlet-SVR和ARIMA分别预测通过Mallat小波分解和单支重构得到的近似信号和多尺度细节信号，最后通过线性叠加得到最终预测结果.通过仿真实验分别对比分析了基于径向基核函数的支持向量机回归算法和ARIMA预测模型，通过3种误差评估得知该组合模型具有更高的预测精度.

关键词: 流量预测, 小波核函数, Morlet支持向量机回归算法, 自回归积分滑动平均模型

Abstract:

According to the nonlinear and multi-dimensional dynamic characteristics of network traffic, combined with the ability of multi-scale wavelet analysis, a comprehensive forecasting model based on Morlet-support vector regression (Morlet-SVR) and auto regressive integrated moving average (ARIMA) was proposed, in which Morlet-SVR and ARIMA are employed to forecast the approximate signal and the multi-scale detail signals respectively by use of Mallet wavelet decomposition and single reconstruction. The final prediction result is obtained by linear superposition of the layers. Simulations give out comparisons with radial basis function-support vector regression and ARIMA model respectively, the proposed model shows higher prediction accuracy by comparison with three error evaluation measurements.

Key words: traffic prediction, wavelet kernel function, Morlet-support vector regression, auto regressive integrated moving average

中图分类号:

TP393

赵建龙, 曲桦, 赵季红, 戴慧珺. 基于Morlet-SVR和ARIMA组合模型的网络流量预测[J]. 北京邮电大学学报, 2016, 39(2): 53-57.

ZHAO Jian-long, QU Hua, ZHAO Ji-hong, DAI Hui-jun. A Comprehensive Forecasting Model for Network Traffic Based on Morlet-SVR and ARIMA[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2016, 39(2): 53-57.

参考文献

[1] Chen Bor-sen, Peng Sen-chueh, Wang Ku-chen. Traffic modeling, prediction, and congestion control for high-speed networks:a fuzzy AR approach[J]. IEEE Transactions on Fuzzy Systems, 2000, 8(5):491-508.
[2] 邹柏贤, 刘强. 基于ARMA模型的网络流量预测[J]. 计算机研究与发展, 2002, 39(12):1645-1652. Zou Boxian, Liu Qiang. ARMA-based traffic prediction and overload detection of network[J]. Journal of Computer Research and Development, 2002, 39(12):1645-1652.
[3] Wang Jin. A process level network traffic prediction algorithm based on ARIMA model in smart substation[C]//IEEE Signal Processing, Communication and Computing (ICSPCC). Kunming:IEEE, 2013:1-5.
[4] 陈晓天, 刘静娴. 改进的基于小波变换和FARIMA模型的网络流量预测算法[J]. 通信学报, 2011, 32(4):153-157. Chen Xiaotian, Liu Jingxian. Network traffic prediction based on wavelet transformation and FARIMA[J]. Journal on Communications, 2011, 32(4):153-157.
[5] Zhang Kun, Chai Yinping, Fu Xing-an. A network traffic prediction model based on recurrent wavelet neural network[C]//IEEE Computer Science and Network Technology (ICCSNT). Changchun:IEEE, 2012:1630-1633.
[6] Qu Hua, Ma Wentao, Zhao Jihong, et al. Prediction method for network traffic based on maximum correntropy criterion[J]. China Communications, 2013, 10(1):134-145.
[7] Wei Xianmin. Supporting vector-machine prediction of network traffic[C]//IEEE Electrical and Control Engineering (ICECE). Yichang:IEEE, 2011:3203-3206.
[8] 李元诚, 方廷健. 小波支持向量机[J]. 模式识别与人工智能, 2004, 17(2):167-172. Li Yuancheng, Fang Tingjian. Wavelet support vector machines[J]. Pattern Recognition and Artificial Intelligence, 2004, 17(2):167-172.
[9] 陈维荣, 郑永康, 戴朝华, 等. 基于复Morlet小波SVM的负荷预测[J]. 西南交通大学学报, 2009, 44(5):631-636. Chen Weirong, Zheng Yongkang, Dai Chaohua, et al. Short-term load forecasting based on complex Morlet wavelet SVM[J]. Journal of Southwest Jiaotong University, 2009, 44(5):631-636.
[10] Waikato. Waikato Internet traffic storage(WITS)[EB/OL]. Waikato:Wand Network Research Group(2011)
[2011] .http://wand.net.nz/wits/waikato/8/20110520-000000-0.php.

基于Morlet-SVR和ARIMA组合模型的网络流量预测

A Comprehensive Forecasting Model for Network Traffic Based on Morlet-SVR and ARIMA

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	牟晓惠, 李丽香. Dropout回声状态网络的网络流量预测[J]. 北京邮电大学学报, 2021, 44(5): 10-13,20.
[2]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
[3]	赵季红, 王明欣, 曲桦, 谢志勇, 刘熙. 一种基于自适应KLMS的卫星网络流量预测算法[J]. 北京邮电大学学报, 2018, 41(3): 51-55.
[4]	肖甫, 赵帅帅, 王少辉, 王汝传, 徐思雅. 基于智能优化的分布式网络流量预测方法[J]. 北京邮电大学学报, 2015, 38(s1): 45-48.
[5]	孙韩林，金跃辉，崔毅东，程时端. 粗粒度网络流量的灰色模型预测[J]. 北京邮电大学学报, 2010, 33(1): 7-11.