An Empirical Investigation of the Impact of Server Virtualization on Energy Efficiency for Green Data Center

Jin, Yichao; Wen, Yonggang; Chen, Qinghua; Zhu, Zuqing

doi:10.1093/comjnl/bxt017

Cited by 42 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…IaaS CMSs, such as OpenStack [8], use VMs to partition a cluster, run one DCS per partition, and let each DCS to manage and schedule submitted applications [11].…”

Section: B Related Work: Cluster Management Systemsmentioning

confidence: 99%

Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach

Sun

Wen

et al. 2017

2017 IEEE International Conference on Smart Computing (SMARTCOMP)

View full text Add to dashboard Cite

Many cluster management systems (CMSs) have been proposed to share a single cluster with multiple distributed computing systems. However, none of the existing approaches can handle distributed machine learning (ML) workloads given the following criteria: high resource utilization, fair resource allocation and low sharing overhead. To solve this problem, we propose a new CMS named Dorm, incorporating a dynamicallypartitioned cluster management mechanism and an utilizationfairness optimizer. Specifically, Dorm uses the container-based virtualization technique to partition a cluster, runs one application per partition, and can dynamically resize each partition at application runtime for resource efficiency and fairness. Each application directly launches its tasks on the assigned partition without petitioning for resources frequently, so Dorm imposes flat sharing overhead. Extensive performance evaluations showed that Dorm could simultaneously increase the resource utilization by a factor of up to 2.32, reduce the fairness loss by a factor of up to 1.52, and speed up popular distributed ML applications by a factor of up to 2.72, compared to existing approaches. Dorm's sharing overhead is less than 5% in most cases.

show abstract

“…IaaS CMSs, such as OpenStack [8], use VMs to partition a cluster, run one DCS per partition, and let each DCS to manage and schedule submitted applications [11].…”

Section: B Related Work: Cluster Management Systemsmentioning

confidence: 99%

Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach

Sun

Wen

et al. 2017

2017 IEEE International Conference on Smart Computing (SMARTCOMP)

View full text Add to dashboard Cite

show abstract

“…Among them, CPU plays the most important role in power consumption. Specially, [15,16,18] has observed a linear relationship between CPU utilization and power consumption. Moreover, several studies and experiments have found that an idle server consumes about 60 % of the peak power [12].…”

Section: Energy Modelmentioning

confidence: 99%

Improving Energy Efficiency for Mobile Media Cloud via Virtual Machine Consolidation

et al. 2015

View full text Add to dashboard Cite

Mobile media applications are on the rise due to the explosive popularity of mobile devices. Advances in mobile media cloud (MMC) make it a promising solution to serve those huge multimedia applications. In MMC, virtualization is adopted to allocate resources elastically from a shared resource pool. Therefore, effective virtual machine (VM) consolidation is of paramount importance to maximize energy efficiency. In this paper, we consider a scenario that mobile media cloud performs video streaming and transcoding for viewers with different mobile devices. We formulate the VM consolidation problem as a mixed integer linear programming. Under this framework, the minimum energy consumption and the number of physical machines (PMs) in operation are derived. Based on these analytical results, for homogeneous media cloud, we develop an approximation algorithm for VM consolidation and placement which jointly considers CPU and bandwidth constraints. For heterogeneous media cloud, we derive an upper and a lower bound of the number of PMs and their energy consumption. Trace-driven simulations demonstrate that our proposed algorithm significantly reduces energy consumption and the number of PMs used.

show abstract

“…Among those impacting factors, CPU plays the most important role in power consumption. Specially, [11], [12] has observed a linear relationship between CPU utilization and power consumption. Moreover, several studies and experiments have found that an idle server consumes about 60% of the peak power [13].…”

Section: Energy Modelmentioning

confidence: 99%

Energy efficient virtual machine consolidation in mobile media cloud

Dong

Zhou

Chen

et al. 2015

2015 Picture Coding Symposium (PCS)

View full text Add to dashboard Cite

Recently, attracted by the abundant computation and networking resources in the cloud, an increased number of mobile media services have been hosted by the cloud computing platforms. These mobile media clouds (MMCs) run hundreds of thousands of servers and consume megawatts of power with massive carbon emission. Virtualization is adopted to allocate resources elastically from a shared resource pool. Therefore, effective virtual machine (VM) consolidation is of paramount importance to reduce energy consumption. We especially focus on applications with different resource (e.g., CPU, memory, network) demands. In this paper, we formulate this problem as a mixed integer linear programming (MILP) problem. We prove that the optimal energy efficiency can be obtained for a homogeneous cloud. Based on this analytical result, we develop an approximation algorithm for VM consolidation and placement which jointly considers CPU and network constraints. Through extensive simulations, we validate the effectiveness of the proposed algorithm.

show abstract

An Empirical Investigation of the Impact of Server Virtualization on Energy Efficiency for Green Data Center

Cited by 42 publications

References 29 publications

Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach

Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach

Improving Energy Efficiency for Mobile Media Cloud via Virtual Machine Consolidation

Energy efficient virtual machine consolidation in mobile media cloud

Contact Info

Product

Resources

About