Analysis of End-to-End Techniques for Bottleneck Bandwidth & Path Capacity Estimation

This paper presents a new passive technique for estimating the bottleneck bandwidth based on transferring the Gaussian kernel density estimation of the packets inter arrival times to the frequency domain, the resultant spectrum contains information about the transmission time of the bottleneck link and can reveal information about multiple bottlenecks if they exist along the end-to-end path. The advantage of the technique is that it provides a model that can be manipulated by the digital signal processing methods which is different than the previous work done in this field that relies too much on statistical methods. The new technique was validated using the ns2 network simulator, several topologies and traffic sources were tried. The post-simulation analysis was done by the programs and Unix/Linux Bourne (and Bash) Shell scripts developed for this purpose. In addition to that, some experiments were conducted to test the strength of the patterns between flows that share a bottleneck by applying K-means algorithm to cluster the average packets inter arrival times of these flows. The document also presents the results of real traffic experiments conducted in an attempt to infer both the bottleneck bandwidth and the capacity of the path using a passive approach