A Novel Wireless Resource Allocation Algorithm in Hybrid Data Center Networks
Résumé
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.