Tools
Tools
Kulkarni, P.G., McClean, S.I., Parr, G.P. 
ORCID: https://orcid.org/0000-0002-9365-9132 and Black, M.M.
(2006)
Proactive predictive queue management for improved QoS in IP networks.
In: UNSPECIFIED.
Abstract
The pursuit of efficient IP resource management has been the main thrust behind Active Queue Management (AQM) research. Random Early Detection (RED), the defacto standard and its different flavours have been proposed as simple solutions to the AQM problem. These approaches, however, are known to suffer from problems like parameter sensitivity and inability to capture variations in the input traffic accurately, thereby resulting in unstable behaviour. This paper presents a proactive prediction based queue management scheme called PAQMAN that captures variations in the underlying traffic accurately and regulates the queue size around the desirable operating point. PAQMAN harnesses the predictability in the underlying traffic by applying the Recursive Least Squares (RLS) algorithm to estimate the average queue length for the next prediction interval given the average queue length information of the past intervals. This predicted average queue length then drives the computation of the packet drop probability. The performance of PAQMAN has been evaluated and compared against the RED scheme through ns-2 simulations that encompass a wide variety of network conditions. In addition to its simplicity and a negligible computational overhead, PAQMAN maintains a relatively low queue size, high link utilization and low packet loss (and hence better Quality of Service (QoS)) in comparison to RED as is shown by our simulation results. Moreover, it does not maintain any per flow state and hence scalability is not an issue.
| Item Type: | Conference or Workshop Item (Other) |
|---|---|
| Faculty \ School: | Faculty of Science > School of Computing Sciences |
| UEA Research Groups: | Faculty of Science > Research Groups > Smart Emerging Technologies Faculty of Science > Research Groups > Cyber Security Privacy and Trust Laboratory Faculty of Science > Research Groups > Data Science and AI |
| Depositing User: | Pure Connector |
| Date Deposited: | 24 Sep 2016 01:07 |
| Last Modified: | 10 Dec 2024 01:15 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/60548 |
| DOI: | 10.1109/ICNICONSMCL.2006.175 |
Actions (login required)
 |
View Item |