Congestion management of self similar IP traffic using normal and exponential marking RED

Abstract

Schemes described in the literature on network congestion management are in general based on queue management. It is widely accepted that Poisson model is not sufficient to characterize the traffic in current Internet. In this paper, we present an alternate RED (Random Early Detection) algorithm for traffic congestion management in IP networks having self-similar (SS) input. We first discuss the basic scheme of Normal and Gentle RED as proposed by Floyd et.al., for the Poisson input model, and then explain piecewise RED, an extension of Gentle RED and Exponential RED - a new AQM proposed by us. We then explain the modification to these algorithms that we propose for the self-similar IP traffic input. Our modification takes into consideration probability values corresponding to the average queue lengths for computing the marking/dropping probability. Verification of the algorithms proposed viz., Normal SS RED and Exponential SS RED, vis-a-vis that of Floyd has been done using simulated self-similar traffic. Results of the verification have been discussed in the paper.