Web traffic demand forecasting using wavelet-based multiscale decomposition

Alex Aussem, Fionn Murtagh

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In this paper we propose an experimental forecasting strategy taking into account the long-range dependence of aggregate network traffic, and we apply it to provide one-minute-ahead World-Wide Web (Web) traffic demand forecasts in terms of average number of bytes transferred. Recently, statistical examination of Web traces have shown evidence that Web traffic arising from file transfers exhibits a behavior that is consistent with the notion of self-similarity. Essentially, self-similarity indicates that significant burstiness is present on a wide range of time scales (i.e., the process is long-range dependent). Hence the idea of exploiting this multiscale property with a view towards discovering and capturing regularities underlying the time series which may prove useful for short-term traffic load forecasting. We carry out a wavelet transform decomposition of the original series to decompose the traffic time series into varying scales of temporal resolution, with the aim of making the underlying temporal structures more tractable. In a second step, each individual wavelet series - supposed to capture some features of the series - is fitted with a dynamical recurrent neural network (DRNN) model to output the wavelet forecast. The latter are afterwards recombined to form the next-minute Web Traffic demand. The method is applied on a large set of HTTP logs and is shown to yield good results.

Original languageEnglish
Pages (from-to)215-236
Number of pages22
JournalInternational Journal of Intelligent Systems
Volume16
Issue number2
Early online date2 Jan 2001
Publication statusPublished - 1 Feb 2001
Externally publishedYes

Fingerprint

Demand Forecasting
World Wide Web
Time series
Wavelets
Traffic
Decomposition
Decompose
HTTP
Recurrent neural networks
Wavelet transforms
Self-similarity
Series
Forecast
Load Forecasting
Long-range Dependence
Recurrent Neural Networks
Network Traffic
Neural Network Model
Large Set
Range of data

Cite this

@article{e6c1a9cb96b9439a9c50e8073857bbc0,
title = "Web traffic demand forecasting using wavelet-based multiscale decomposition",
abstract = "In this paper we propose an experimental forecasting strategy taking into account the long-range dependence of aggregate network traffic, and we apply it to provide one-minute-ahead World-Wide Web (Web) traffic demand forecasts in terms of average number of bytes transferred. Recently, statistical examination of Web traces have shown evidence that Web traffic arising from file transfers exhibits a behavior that is consistent with the notion of self-similarity. Essentially, self-similarity indicates that significant burstiness is present on a wide range of time scales (i.e., the process is long-range dependent). Hence the idea of exploiting this multiscale property with a view towards discovering and capturing regularities underlying the time series which may prove useful for short-term traffic load forecasting. We carry out a wavelet transform decomposition of the original series to decompose the traffic time series into varying scales of temporal resolution, with the aim of making the underlying temporal structures more tractable. In a second step, each individual wavelet series - supposed to capture some features of the series - is fitted with a dynamical recurrent neural network (DRNN) model to output the wavelet forecast. The latter are afterwards recombined to form the next-minute Web Traffic demand. The method is applied on a large set of HTTP logs and is shown to yield good results.",
author = "Alex Aussem and Fionn Murtagh",
year = "2001",
month = "2",
day = "1",
language = "English",
volume = "16",
pages = "215--236",
journal = "International Journal of Intelligent Systems",
issn = "0884-8173",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

Web traffic demand forecasting using wavelet-based multiscale decomposition. / Aussem, Alex; Murtagh, Fionn.

In: International Journal of Intelligent Systems, Vol. 16, No. 2, 01.02.2001, p. 215-236.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Web traffic demand forecasting using wavelet-based multiscale decomposition

AU - Aussem, Alex

AU - Murtagh, Fionn

PY - 2001/2/1

Y1 - 2001/2/1

N2 - In this paper we propose an experimental forecasting strategy taking into account the long-range dependence of aggregate network traffic, and we apply it to provide one-minute-ahead World-Wide Web (Web) traffic demand forecasts in terms of average number of bytes transferred. Recently, statistical examination of Web traces have shown evidence that Web traffic arising from file transfers exhibits a behavior that is consistent with the notion of self-similarity. Essentially, self-similarity indicates that significant burstiness is present on a wide range of time scales (i.e., the process is long-range dependent). Hence the idea of exploiting this multiscale property with a view towards discovering and capturing regularities underlying the time series which may prove useful for short-term traffic load forecasting. We carry out a wavelet transform decomposition of the original series to decompose the traffic time series into varying scales of temporal resolution, with the aim of making the underlying temporal structures more tractable. In a second step, each individual wavelet series - supposed to capture some features of the series - is fitted with a dynamical recurrent neural network (DRNN) model to output the wavelet forecast. The latter are afterwards recombined to form the next-minute Web Traffic demand. The method is applied on a large set of HTTP logs and is shown to yield good results.

AB - In this paper we propose an experimental forecasting strategy taking into account the long-range dependence of aggregate network traffic, and we apply it to provide one-minute-ahead World-Wide Web (Web) traffic demand forecasts in terms of average number of bytes transferred. Recently, statistical examination of Web traces have shown evidence that Web traffic arising from file transfers exhibits a behavior that is consistent with the notion of self-similarity. Essentially, self-similarity indicates that significant burstiness is present on a wide range of time scales (i.e., the process is long-range dependent). Hence the idea of exploiting this multiscale property with a view towards discovering and capturing regularities underlying the time series which may prove useful for short-term traffic load forecasting. We carry out a wavelet transform decomposition of the original series to decompose the traffic time series into varying scales of temporal resolution, with the aim of making the underlying temporal structures more tractable. In a second step, each individual wavelet series - supposed to capture some features of the series - is fitted with a dynamical recurrent neural network (DRNN) model to output the wavelet forecast. The latter are afterwards recombined to form the next-minute Web Traffic demand. The method is applied on a large set of HTTP logs and is shown to yield good results.

UR - http://www.scopus.com/inward/record.url?scp=0035251819&partnerID=8YFLogxK

UR - https://onlinelibrary.wiley.com/doi/10.1002/1098-111X%28200102%2916%3A2%3C215%3A%3AAID-INT50%3E3.0.CO%3B2-%23

M3 - Article

VL - 16

SP - 215

EP - 236

JO - International Journal of Intelligent Systems

JF - International Journal of Intelligent Systems

SN - 0884-8173

IS - 2

ER -