Efficient Prediction of Network Traffic for Real-Time Applications

Efficient Prediction of Network Traffic for Real-Time Applications

Accurate real-time traffic prediction is required in many networking applications like dynamic resource allocation and power management. This paper explores a number of predictors and searches for a predictor which has high accuracy and low computation complexity and power consumption. Many predicto...

Full description

Bibliographic Details
Main Authors: Muhammad Faisal Iqbal, Muhammad Zahid, Durdana Habib, Lizy Kurian John
Format: Article
Language:English
Published: Hindawi Limited 2019-01-01
Series:Journal of Computer Networks and Communications
Online Access:http://dx.doi.org/10.1155/2019/4067135
id doaj-6f89e9ea606f480f87b01bcc637f2a0e
record_format Article
spelling doaj-6f89e9ea606f480f87b01bcc637f2a0e2020-11-24T21:40:45ZengHindawi LimitedJournal of Computer Networks and Communications2090-71412090-715X2019-01-01201910.1155/2019/40671354067135Efficient Prediction of Network Traffic for Real-Time ApplicationsMuhammad Faisal Iqbal0Muhammad Zahid1Durdana Habib2Lizy Kurian John3Capital University of Science and Technology, Islamabad, PakistanCentre of Excellence in Science and Applied Technologies, Islamabad, PakistanNational University of Computer and Emerging Sciences, Islamabad, PakistanThe University of Texas at Austin, Austin, TX, USAAccurate real-time traffic prediction is required in many networking applications like dynamic resource allocation and power management. This paper explores a number of predictors and searches for a predictor which has high accuracy and low computation complexity and power consumption. Many predictors from three different classes, including classic time series, artificial neural networks, and wavelet transform-based predictors, are compared. These predictors are evaluated using real network traces. Comparison of accuracy and cost, both in terms of computation complexity and power consumption, is presented. It is observed that a double exponential smoothing predictor provides a reasonable tradeoff between performance and cost overhead.http://dx.doi.org/10.1155/2019/4067135
collection DOAJ
language English
format Article
sources DOAJ
author Muhammad Faisal Iqbal
Muhammad Zahid
Durdana Habib
Lizy Kurian John
spellingShingle Muhammad Faisal Iqbal
Muhammad Zahid
Durdana Habib
Lizy Kurian John
Efficient Prediction of Network Traffic for Real-Time Applications
Journal of Computer Networks and Communications
author_facet Muhammad Faisal Iqbal
Muhammad Zahid
Durdana Habib
Lizy Kurian John
author_sort Muhammad Faisal Iqbal
title Efficient Prediction of Network Traffic for Real-Time Applications
title_short Efficient Prediction of Network Traffic for Real-Time Applications
title_full Efficient Prediction of Network Traffic for Real-Time Applications
title_fullStr Efficient Prediction of Network Traffic for Real-Time Applications
title_full_unstemmed Efficient Prediction of Network Traffic for Real-Time Applications
title_sort efficient prediction of network traffic for real-time applications
publisher Hindawi Limited
series Journal of Computer Networks and Communications
issn 2090-7141
2090-715X
publishDate 2019-01-01
description Accurate real-time traffic prediction is required in many networking applications like dynamic resource allocation and power management. This paper explores a number of predictors and searches for a predictor which has high accuracy and low computation complexity and power consumption. Many predictors from three different classes, including classic time series, artificial neural networks, and wavelet transform-based predictors, are compared. These predictors are evaluated using real network traces. Comparison of accuracy and cost, both in terms of computation complexity and power consumption, is presented. It is observed that a double exponential smoothing predictor provides a reasonable tradeoff between performance and cost overhead.
url http://dx.doi.org/10.1155/2019/4067135
work_keys_str_mv AT muhammadfaisaliqbal efficientpredictionofnetworktrafficforrealtimeapplications
AT muhammadzahid efficientpredictionofnetworktrafficforrealtimeapplications
AT durdanahabib efficientpredictionofnetworktrafficforrealtimeapplications
AT lizykurianjohn efficientpredictionofnetworktrafficforrealtimeapplications
_version_ 1725924719433089024

Similar Items