Modern networks carry a wide range of different data types, each with its own individual
requirements. The scheduler plays an important role in enabling a network to meet all
these requirements. In wired networks a large amount of research has been performed
on various schedulers, most of which belong to the family of General Processor Sharing
(GPS) schedulers. In this dissertation we briefly discuss the work that has been done on a
range of wired schedulers, which all attempt to differentiate between heterogeneous traffic.
In the world of wireless communications the scheduler plays a very important role, since
it can take channel conditions into account to further improve the performance of the
network. The main focus of this dissertation is to introduce schedulers, which attempt to
meet the Quality of Service requirements of various data types in a wireless environment.
Examples of schedulers that take channel conditions into account are the Modified Largest
Weighted Delay First (M-LWDF), as well as a new scheduler introduced in this dissertation,
known as the Wireless Fair Largest Weighted Delay First (WF-LWDF) algorithm.
The two schemes are studied in detail and a comparison of their throughput, delay, power,
and packet dropping performance is made through a range of simulations. The results are
compared to the performance offour other schedulers. The fairness ofM-LWDF and WFLWDF
is determined through simulations. The throughput results are used to establish
Chernoff bounds of the fairness of these two algorithms. Finally, a summary is given of the
published delay bounds of various schedulers, and the tightness of the resultant bounds is
discussed. / Thesis (M.Sc. Eng.)-University of Natal, Durban, 2003.
Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:ukzn/oai:http://researchspace.ukzn.ac.za:10413/4206 |
Date | 10 November 2011 |
Creators | Scriba, Stefan Martin. |
Contributors | Takawira, Fambirai. |
Source Sets | South African National ETD Portal |
Language | English |
Detected Language | English |
Type | Thesis |
Page generated in 0.0023 seconds