An Enhanced Scalable Proximity Model - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Other Publications Year : 2005

An Enhanced Scalable Proximity Model

Mohammad Malli
  • Function : Author
  • PersonId : 831387
Chadi Barakat
Walid Dabbous


We introduce in this paper the notion of application-level proximity. This proximity is a function of network parameters that decide on the application performance, mainly the delay and the available bandwidth. Most of existing protocols rely on the delay proximity (e.g., the delay closest peer is the best peer to contact). We motivate the need for this new notion by showing that the proximity in the delay space does not automatically lead to a proximity in the bandwidth space. Then, we explain how a landmark approach, designed originally to estimate the delay proximity among peers in a scalable manner, can be extended to account for the available bandwidth. Our solution estimates the bandwidth among peers using the bandwidth of the indirect paths that join them via a small set of landmarks. We evaluate the solution and analyze the impact of the landmarks' locations on the accuracy of the estimation. We obtain satisfactory results when the delay of more than one indirect path is close to that of the direct path. Better results are obtained when more than one landmark are located near one of the path end points. Finally, we show that the proximity determined using our bandwidth estimation model provides much better quality than that obtained using the delay proximity for large file transfer applications. The whole study is based on real measurements conducted over the Planetlab plateform.
Fichier principal
Vignette du fichier
networking.pdf (120.65 Ko) Télécharger le fichier

Dates and versions

inria-00000902 , version 1 (05-12-2005)


  • HAL Id : inria-00000902 , version 1


Mohammad Malli, Chadi Barakat, Walid Dabbous. An Enhanced Scalable Proximity Model. 2005. ⟨inria-00000902⟩


98 View
115 Download


Gmail Facebook X LinkedIn More