Optimized Protocols and Software for High-Performance Networks

  • Increase font size
  • Default font size
  • Decrease font size

GdT le 24/11/2011 à 14h - Mohamad JABER

E-mail Print

Mohamad Jaber nous présentera ses travaux de recherche le jeudi 24 novembre à 14h00 en salle du conseil (3ème étage). 
Ci-dessous un résumé de sa présentation. 


The Vivaldi algorithm [10] is known to be one of the most interesting approaches for the calculation of Internet coordinates.

It is a fully distributed, light-weight and adaptive algorithm, requiring no fixed network infrastructure and no distinguished nodes.

Recent studies show that host coordinates in the Vivaldi system are not stable and they drift rapidly even when the net- work delays do not change.

In this work, we observe that, despite the instability of Vivaldi coordinates in their absolute values, there is still a stable internal structure that can

better re- flect the stability of the underlying network. We proceed for this study by extensive simulations and experimentations. In the first stage,

we confirm the fact that Vivaldi coordinates oscillate over time because of the adaptive nature of the system. The variations of these coordinates however

are most of the time correlated with each other pointing to some stable cluster of nodes seen from inside the network. In a second stage, we present a new clustering

algorithm based on the Hierarchical Grouping method [57] to identify a cluster of stable nodes once the network and the host coordinates reach their stationary

regime. The metric that we use to cluster nodes in the system is the amount of variation of their Euclidean distances with respect to each other.

Our main finding is that a stable cluster of nodes always exists and that this cluster groups most of the nodes. We highlight the utility of such finding

with an application that tracks changes in network delays. To this end, we propose to track a simple signal, which is the size of this biggest stable cluster.

By changing artificially the network delays in different scenarios, we show that these changes are easily reflected by this body of stable nodes, hence allowing

to obtain a global picture about the stability of the underlying network without the need for exhaustive delay measurements.

Last Updated on Thursday, 17 November 2011 15:51