High speed network impacts and power consumption estimation for cloud data centers

Abstract

Networking technology in data centers is limited by Ethernet speed, and a standard for 10 Tbps Ethernet is already envisioned. In this paper, we seek to understand and analyze the energy impact of increasing the network speed in the energy consumption in data centers that operate in a cloud with virtual machine migration. We consider four scheduling algorithms of virtual machines for workload scheduling. Results obtained by simulation show that from the energy consumption point of view, the bandwidth of non-federated data centers significantly impacts the intra cloud scheduling process, and this should be considered when choosing a scheduling algorithm. We also found that the makespan has minimal impact with this increased bandwidth in data centers, while the number of migrations increases greatly. We also develop an empirical model to estimate the power consumption based on bandwidth for studied scenarios, where there is an upper limit of bandwidth that impacts the energy consumption, after which virtually no changes are noticed.