A Short-Term Forecasting Algorithm for Network Traffic Based on Chaos Theory and SVM.

Saved in:

Bibliographic Details
Title:	A Short-Term Forecasting Algorithm for Network Traffic Based on Chaos Theory and SVM.
Authors:	Liu, Xingwei lxw@mail.xhu.edu.cn, Fang, Xuming¹ xmfang@swjtu.edu.cn, Qin, Zhenhua² qinzhenhua-xh@163.com, Ye, Chun² feng_yechun@163.com, Xie, Miao² clifford1984621@gmail.com
Source:	Journal of Network & Systems Management. Dec2011, Vol. 19 Issue 4, p427-447. 21p.
Subjects:	Computer network security software, Time series analysis software, Computer network traffic, Chaos theory, Support vector machines, Internet traffic, Forecasting, Computer software
Abstract:	Recently, the forecasting technologies for network traffic have played a significant role in network management, congestion control and network security. Forecasting algorithms have also been investigated for decades along with the development of Time Series Analysis (TSA). Chaotic Time Series Analysis (CTSA) may be used to model and forecast the time series by Chaos Theory. As one of the prevailing intelligent forecasting algorithms, it is worthwhile to integrate CTSA and Support Vector Machine (SVM). In this paper, after the vulnerabilities of Local Support Vector Machine (LSVM) in forecasting modeling are analyzed, the Dynamic Time Wrapping (DTW) and the 'Dynamic K' strategy are introduced, as well as a short-term network traffic forecasting algorithm LSVM-DTW-K based on Chaos Theory and SVM is presented. Finally, two sets of network traffic datasets collected from wired and wireless campus networks, respectively, are studied for our experiments. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Network & Systems Management is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Recently, the forecasting technologies for network traffic have played a significant role in network management, congestion control and network security. Forecasting algorithms have also been investigated for decades along with the development of Time Series Analysis (TSA). Chaotic Time Series Analysis (CTSA) may be used to model and forecast the time series by Chaos Theory. As one of the prevailing intelligent forecasting algorithms, it is worthwhile to integrate CTSA and Support Vector Machine (SVM). In this paper, after the vulnerabilities of Local Support Vector Machine (LSVM) in forecasting modeling are analyzed, the Dynamic Time Wrapping (DTW) and the 'Dynamic K' strategy are introduced, as well as a short-term network traffic forecasting algorithm LSVM-DTW-K based on Chaos Theory and SVM is presented. Finally, two sets of network traffic datasets collected from wired and wireless campus networks, respectively, are studied for our experiments. [ABSTRACT FROM AUTHOR]
ISSN:	10647570
DOI:	10.1007/s10922-010-9188-3