Efficient Traffic Flow Measurement for ISP Networks - Archive ouverte HAL
Communication Dans Un Congrès Année : 2012

Efficient Traffic Flow Measurement for ISP Networks

Résumé

Traffic flow measurement is of great importance to ISPs for various network engineering tasks. However, directly measuring traffic flows of the whole ISP network is greatly time and cost-consuming. An interesting problem is that how one can obtain the traffic flows of the whole ISP network by just monitoring a small fraction of links. Previous works view the problem as Vertex Cover problem. They suffer from high time complexity. Besides, using these methods, the monitoring of some links is redundant. Different from these works, we study the problem from the perspective of edges and propose two models. The first model, Extended Edge Cover model, is based on the key observation of flow conservation. This method can determine the minimum set of monitored links, which are 30% less than that of previous works. The second model, shared-path model, utilizes the routing information and topological property of the network. It is more suitable when the monitoring resources are limited but one still wants to measure a large part of the networks. Using this method, one can measure 85% of the network by monitoring 5% of links. Finally, we evaluate the performance of the two models through extensive simulations. The experimental results show the effectiveness and robustness of the two models.
Fichier principal
Vignette du fichier
1569609915.pdf (674.51 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00737733 , version 1 (25-10-2013)

Identifiants

  • HAL Id : hal-00737733 , version 1

Citer

Qinghua Wu, Zhenyu Li, Jianhua Yang, Gaogang Xie, Kavé Salamatian. Efficient Traffic Flow Measurement for ISP Networks. 37th Annual IEEE Conference on Local Computer Networks (LCN 2012), Oct 2012, Clearwater, Florida, United States. pp.352-355. ⟨hal-00737733⟩
108 Consultations
440 Téléchargements

Partager

More