By Topic

A new service classification strategy in hybrid scheduling to support differentiated QoS in wireless data networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
N. Saxena ; Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA ; K. Basu ; S. K. Das ; C. M. Pinotti

In this paper we have developed a new service classification strategy in hybrid scheduling scheme to support differentiated quality of service (QoS) among the different set of clients. The scheme dynamically computes the data access probabilities and amalgamates the push and pull scheduling schemes to develop the hybrid scheduling framework. While a flat scheduling is used for push system, the major novelty of the work lies in differentiating the clients based on their priority-classes and incorporating the effect of priority in selecting an item from the pull-system. Modeling and analysis of the system is performed to get an average behavior of the QoS parameters like delay in our hybrid scheduling framework. Simulation results points out that the average waiting time for the highest priority clients can be kept very low, while simultaneously minimizing the number of requests dropped by assigning appropriate fraction of available bandwidth. It also demonstrates that by intelligent selection of the cut-off point, used to segregate push and pull systems, the overall cost associated with the system can be minimized.

Published in:

2005 International Conference on Parallel Processing (ICPP'05)

Date of Conference:

14-17 June 2005