Energy efficiency of VM consolidation in IaaS clouds

Abstract

The energy efficiency of cloud computing has recently attracted a great deal of attention. As a result of raised expectations, cloud providers such as Amazon and Microsoft have started to deploy a new IaaS service, a MapReduce-style virtual cluster, to process data-intensive workloads. Considering that the IaaS provider supports multiple pricing options, we study batch-oriented consolidation and online 123 F. Teng et al. placement for reserved virtual machines (VMs) and on-demand VMs, respectively. For batch cases, we propose a DVFS-based heuristic TRP-FS to consolidate virtual clusters on physical servers to save energy while guarantee job SLAs. We prove the most efficient frequency that minimizes the energy consumption, and the upper bound of energy saving through DVFS techniques. More interestingly, this frequency only depends on the type of processor. FS can also be used in combination with other consolidation algorithms. For online cases, a time-balancing heuristic OTB is designed for on-demand placement, which can reduce the mode switching by means of balancing server duration and utilization. The experimental results both in simulation and using the Hadoop testbed show that our approach achieves greater energy savings than existing algorithms.

Which is the best algorithm for virtual machine placement optimization?

“…Most works consider the placement of all VMs in the DC at once , . However, some also consider the placement of a single VM or a set of VMs belonging to the same application New placement vs re‐optimization.…”

“…2,20,25,26,31,36,[40][41][42][43][44] However, some also consider the placement of a single VM 11,45 or a set of VMs belonging to the same application. 24,46,47 • New placement vs re-optimization. For the given VM set (whether it is the set of all VMs of the DC, a single VM, or the VMs of an application), there are 2 different problem variants: Either the initial placement of the VMs needs to be determined 11,19,31,41,46,48 or their existing placement is to be re-optimized to adapt it to the changed resource requirements of the workload.…”

Modelling resource heterogeneities in cloud simulations and quantifying their accuracy

“…Teng et. al [26] also found a linear relationship between a DVFS enabled CPU and its power consumption as given in Eq. 5:…”

An Adaptive Autonomic Framework for Optimizing Energy Consumption in the Cloud Data Centers

“…30-70% of their maximum load which consumes power. In some research, they consolidate all the workload in a number of servers at a given time [11][12][13] and power off unused servers or at least make them work in low power mode. And consolidation can be performed at various levels: (a) VM consolidation, (b) server consolidation, and (c) task consolidation.…”