UUM Repository | Universiti Utara Malaysian Institutional Repository
FAQs | Feedback | Search Tips | Sitemap

A quantitative analysis and performance study of fast congestion notification (FN) mechanism

M. Kadhum, Mohammed and Hassan, Suhaidi (2009) A quantitative analysis and performance study of fast congestion notification (FN) mechanism. In: Proceedings of the 15th Asia-Pacific Conference on Communications (APCC'09), 8-10 October 2009, Shanghai. IEEE Computer Society, pp. 749-753. ISBN 978-1-4244-4784-8

Download (286kB) | Preview


Congestion in computer network happens when the number of transmission requests exceeds the transmission capacity at a certain network point (called a bottle-neck resource) at a specific time. Congestion usually causes buffers overflow and packets loss. The purpose of congestion management is to maintain a balance between the transmission requests and the transmission capacity so that the bottle-neck resources operate on an optimal level, and the sources are offered service in a way that assures fairness. Fast Congestion Notification (FN) is one of the proactive queue management mechanisms that limits the queuing delay and achieves the maximum link utilization possible with minimum packet drops. In this paper we present a detailed performance comparison of the Linear FN algorithm to RED based on the results obtained through simulations. The paper shows how FN can be tuned for different window size (Ws) and periods of time constant (T) to achieve higher link utilization; reduce the queuing delay, and lower packet drop ratio.

Item Type: Book Section
Uncontrolled Keywords: Internet Congestion; Active Queue Management(AQM); Explicit Congestion Notification (ECN); Gateway buffers; Random Early Detection(RED)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: College of Arts and Sciences
Depositing User: Prof. Dr. Suhaidi Hassan
Date Deposited: 16 Feb 2011 09:49
Last Modified: 16 Feb 2011 09:49
URI: http://repo.uum.edu.my/id/eprint/2141

Actions (login required)

View Item View Item