A Novel Wireless Resource Allocation Algorithm in Hybrid Data Center Networks

B. Dab 1 I. Fajjari N. Aitsaadi 1 A. Mellouk 1
1 CIR
LISSI - Laboratoire Images, Signaux et Systèmes Intelligents
Abstract : To this day, Cloud computing continues its explosive growth. Nevertheless, with the exceptional evolution of demands, data centers are suffering from congestion problems. To deal with these resource limitations, first, we put forward a novel Hybrid Data Center Network (HDCN) Architecture enabling high throughput wireless (IEEE 802.11 ad) and wired (IEEE 802.3) transmissions. Secondly, we propose a new resource allocation algorithm based on Graph Coloring in HDCN denoted by GC-HDCN. The main objective is to maximize the throughput of intra-HDCN communication requests over the wireless and/or wired infrastructure. The problem is formulated as minimum graph coloring which is NP-Hard. GC-HDCN makes use of i) column generation and ii) branch and price optimization schemes to resolve the assignment of wireless channels. Based on extensive simulations with Qual Net simulator considering all the layers of the protocol stack, the results obtained show that our proposal GC-HDCN outperforms the related prominent strategies in terms of i) end-to-end delay, ii) throughput and iii) spectrum spatial reuse.
Type de document :
Communication dans un congrès
Proc. Of the 12th IEEE International Conference on Mobile Ad hoc and Sensor Systems, MASS 2015, 2015, Dallas, Texas, United States. pp.109- 117, 2015
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01567528
Contributeur : Lab Lissi <>
Soumis le : lundi 24 juillet 2017 - 09:29:12
Dernière modification le : mercredi 20 février 2019 - 13:22:49

Identifiants

  • HAL Id : hal-01567528, version 1

Collections

Citation

B. Dab, I. Fajjari, N. Aitsaadi, A. Mellouk. A Novel Wireless Resource Allocation Algorithm in Hybrid Data Center Networks. Proc. Of the 12th IEEE International Conference on Mobile Ad hoc and Sensor Systems, MASS 2015, 2015, Dallas, Texas, United States. pp.109- 117, 2015. 〈hal-01567528〉

Partager

Métriques

Consultations de la notice

36