Dynamic optimization of power and performance for virtualized server clusters

Petrucci, Vinícius; Loques, Orlando; Mossé, Daniel

doi:10.1145/1774088.1774144

Cited by 35 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their experimental results show near 72% savings in power as compared to static power management techniques and 69.8% additional savings with the global and local optimizations. Petrucci et al [24] developed a mixed integer programming (MIP) formulation to dynamically configure the consolidation of multiple services/applications in a virtualized server cluster. The approach is power efficiency centered and takes into account the cost of turning on/off the servers.…”

Section: Related Workmentioning

confidence: 99%

“…The use of virtualization for consolidation is presented in [25], which proposes a dynamic configuration approach for power optimization in virtualized server clusters and outlines an algorithm to dynamically manage the virtualized server cluster. Following the same idea, [21] aims to reduce virtualized data center power consumption by supporting VM migration and VM placement optimization while reducing the human intervention, but no evaluation is provided.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards energy-aware scheduling in data centers using machine learning

Berral

Goiri

Nou

et al. 2010

Proceedings of the 1st International Conference on Energy-Efficient Computing and Networking

192

109

View full text Add to dashboard Cite

As energy-related costs have become a major economical factor for IT infrastructures and data-centers, companies and the research community are being challenged to find better and more efficient power-aware resource management strategies. There is a growing interest in "Green" IT and there is still a big gap in this area to be covered.In order to obtain an energy-efficient data center, we propose a framework that provides an intelligent consolidation methodology using different techniques such as turning on/off machines, power-aware consolidation algorithms, and machine learning techniques to deal with uncertain information while maximizing performance. For the machine learning approach, we use models learned from previous system behaviors in order to predict power consumption levels, CPU loads, and SLA timings, and improve scheduling decisions. Our framework is vertical, because it considers from watt consumption to workload features, and cross-disciplinary, as it uses a wide variety of techniques.We evaluate these techniques with a framework that covers the whole control cycle of a real scenario, using a simulation with representative heterogeneous workloads, and we measure the quality of the results according to a set of metrics focused toward our goals, besides traditional policies. The results obtained indicate that our approach is close to the optimal placement and behaves better when the level of uncertainty increases.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Towards energy-aware scheduling in data centers using machine learning

Berral

Goiri

Nou

et al. 2010

Proceedings of the 1st International Conference on Energy-Efficient Computing and Networking

192

109

View full text Add to dashboard Cite

show abstract

“…This technique satisfies the demand by different processes retaining the optimization values set for achieving energy utilization. Petrucci [43] proposed a unified framework for large grid computing systems using different techniques such as policies for power off idle nodes, thereby predicting the future load on servers to save power. Capit [44] highlighted different aspects of developing a green IT implementation framework to build green data centers, but this proposal lacks different techniques to focus on the emission of greenhouse gases, proper recycling policy, and service-level agreements between service providers and end users.…”

Section: Related Workmentioning

confidence: 99%

Power Usage Effectiveness Metrics to Measure Efficiency and Performance of Data Centers

Uddin

Alsaqour

Shah

et al. 2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

Abstract:Intensifying computation demand from enterprises has driven the growth of large, multifaceted data centers to manage current Internet, financial, commercial, and business applications. A data center comprises thousands of servers and other equipment that require substantial amounts of power to operate. This condition results in numerous challenges for the data center industry, such as massive energy consumption, underutilization of installed equipment, emission of greenhouse gases, and effect on global warming. This paper highlights the significance of identifying metrics to determine the performance and efficiency of a data center, which can help such a facility achieve operational cost savings through proper implementation of performance-measuring metrics. This paper discusses the implementation of Power Usage Effectiveness metrics in a tier-level data center in Pakistan. The results show that the overall performance value of the facility is 3.3, which indicates poor and inefficient operations.

show abstract

“…A mixed integer programming approach to dynamically configuring the consolidation of multiple services or applications in a virtualised server cluster has been proposed [11]. That work both focuses on power efficiency, and considers the costs of turning on/off the servers.…”

Section: Related Workmentioning

confidence: 99%

Constraint Programming Based Large Neighbourhood Search for Energy Minimisation in Data Centres

Cambazard

Mehta

O’Sullivan

et al. 2013

Economics of Grids, Clouds, Systems, and Services

View full text Add to dashboard Cite

Abstract. EnergeTIC is a recent industrial research project carried out in Grenoble on optimising energy consumption in data centres. We study the problem formulation proposed by EnergeTIC. The problem focuses on the allocation of virtual machines to servers with time-variable resource demands in data centres in order to minimise energy costs while ensuring service quality. We present a scalable constraint programming-based large neighbourhood search (CP-LNS) method to solving this challenging problem. We present empirical results that demonstrate that the industrial benchmarks can be solved to near optimality using our approach. Our CP-LNS method provides a fast and practical approach for finding high quality solutions for lowering electricity costs in data centres.

show abstract

Dynamic optimization of power and performance for virtualized server clusters

Cited by 35 publications

References 6 publications

Towards energy-aware scheduling in data centers using machine learning

Towards energy-aware scheduling in data centers using machine learning

Power Usage Effectiveness Metrics to Measure Efficiency and Performance of Data Centers

Constraint Programming Based Large Neighbourhood Search for Energy Minimisation in Data Centres

Contact Info

Product

Resources

About