Application of neural networks for achieving 802.11 QoS in heterogeneous channels

Chia-Pin Wang, Tsungnan Lin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In error-prone IEEE 802.11 WLAN (Wireless Local Area Network) environments, heterogeneous link qualities can significantly affect channel utilizations of mobile stations and consequently the user-perceived QoS (Quality of Services) of multimedia applications. In this paper we propose a novel optimization framework which provides QoS by adjusting IWSs (Initial Window Size) according to current channel states and QoS requirements. It is a table-driven approach which off-line pre-establishes the table of the best IWSs based on a cost-reward function. Neural networks are utilized to learn the mapping correlation and then to generalize that to other situations of interest. At runtime, the IWS of each user can thus be determined optimally with a simple table lookup rapidly without much time spent on learning about the nonlinear and complicated correlation. A video streaming transmission scenario is used to evaluate the performance of our scheme. The simulation results demonstrate that the proposed mechanism can effectively provide QoS for each user when the capacity of the network is sufficient for the requirements of all users.

Original languageEnglish
Pages (from-to)581-592
Number of pages12
JournalComputer Networks
Volume52
Issue number3
DOIs
Publication statusPublished - 2008 Feb 22

Fingerprint

Quality of service
Neural networks
Table lookup
Video streaming
Wireless local area networks (WLAN)
Cost functions

Keywords

  • IEEE 802.11 WLANs
  • Neural networks
  • QoS

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Application of neural networks for achieving 802.11 QoS in heterogeneous channels. / Wang, Chia-Pin; Lin, Tsungnan.

In: Computer Networks, Vol. 52, No. 3, 22.02.2008, p. 581-592.

Research output: Contribution to journalArticle

@article{d89f8f18602f4f72b897e9327ca0c7d0,
title = "Application of neural networks for achieving 802.11 QoS in heterogeneous channels",
abstract = "In error-prone IEEE 802.11 WLAN (Wireless Local Area Network) environments, heterogeneous link qualities can significantly affect channel utilizations of mobile stations and consequently the user-perceived QoS (Quality of Services) of multimedia applications. In this paper we propose a novel optimization framework which provides QoS by adjusting IWSs (Initial Window Size) according to current channel states and QoS requirements. It is a table-driven approach which off-line pre-establishes the table of the best IWSs based on a cost-reward function. Neural networks are utilized to learn the mapping correlation and then to generalize that to other situations of interest. At runtime, the IWS of each user can thus be determined optimally with a simple table lookup rapidly without much time spent on learning about the nonlinear and complicated correlation. A video streaming transmission scenario is used to evaluate the performance of our scheme. The simulation results demonstrate that the proposed mechanism can effectively provide QoS for each user when the capacity of the network is sufficient for the requirements of all users.",
keywords = "IEEE 802.11 WLANs, Neural networks, QoS",
author = "Chia-Pin Wang and Tsungnan Lin",
year = "2008",
month = "2",
day = "22",
doi = "10.1016/j.comnet.2007.10.007",
language = "English",
volume = "52",
pages = "581--592",
journal = "Computer Networks",
issn = "1389-1286",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Application of neural networks for achieving 802.11 QoS in heterogeneous channels

AU - Wang, Chia-Pin

AU - Lin, Tsungnan

PY - 2008/2/22

Y1 - 2008/2/22

N2 - In error-prone IEEE 802.11 WLAN (Wireless Local Area Network) environments, heterogeneous link qualities can significantly affect channel utilizations of mobile stations and consequently the user-perceived QoS (Quality of Services) of multimedia applications. In this paper we propose a novel optimization framework which provides QoS by adjusting IWSs (Initial Window Size) according to current channel states and QoS requirements. It is a table-driven approach which off-line pre-establishes the table of the best IWSs based on a cost-reward function. Neural networks are utilized to learn the mapping correlation and then to generalize that to other situations of interest. At runtime, the IWS of each user can thus be determined optimally with a simple table lookup rapidly without much time spent on learning about the nonlinear and complicated correlation. A video streaming transmission scenario is used to evaluate the performance of our scheme. The simulation results demonstrate that the proposed mechanism can effectively provide QoS for each user when the capacity of the network is sufficient for the requirements of all users.

AB - In error-prone IEEE 802.11 WLAN (Wireless Local Area Network) environments, heterogeneous link qualities can significantly affect channel utilizations of mobile stations and consequently the user-perceived QoS (Quality of Services) of multimedia applications. In this paper we propose a novel optimization framework which provides QoS by adjusting IWSs (Initial Window Size) according to current channel states and QoS requirements. It is a table-driven approach which off-line pre-establishes the table of the best IWSs based on a cost-reward function. Neural networks are utilized to learn the mapping correlation and then to generalize that to other situations of interest. At runtime, the IWS of each user can thus be determined optimally with a simple table lookup rapidly without much time spent on learning about the nonlinear and complicated correlation. A video streaming transmission scenario is used to evaluate the performance of our scheme. The simulation results demonstrate that the proposed mechanism can effectively provide QoS for each user when the capacity of the network is sufficient for the requirements of all users.

KW - IEEE 802.11 WLANs

KW - Neural networks

KW - QoS

UR - http://www.scopus.com/inward/record.url?scp=38549129251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549129251&partnerID=8YFLogxK

U2 - 10.1016/j.comnet.2007.10.007

DO - 10.1016/j.comnet.2007.10.007

M3 - Article

AN - SCOPUS:38549129251

VL - 52

SP - 581

EP - 592

JO - Computer Networks

JF - Computer Networks

SN - 1389-1286

IS - 3

ER -