Abstract
A data center must serve arriving requests in such way that the energy usage, reliability and quality of service performance should be balanced. This work is devoted to on-line resource allocation policies in data centers. We study a Markovian queueing system with controllable number of servers in order to minimize energy consumption and thus maximize the average revenue earned per unit time. An analytical model approach based on continuous-time Markov chain is proposed. The model is tested by simulation. Combining on-line measurement, prediction and adaptation, our techniques can dynamically determine the number of servers to handle the predicted workload. The policies comply with energy efficiency and service level agreements even under extreme workload fluctuations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kumar, R.: Data Center Power and Cooling Scenario through 2015. Gartner, Inc. (March 2007)
Luh, H., Viniotis, I.: Threshold control policies for heterogeneous server systems. Mathematical Methods of Operations Research 55, 121–142 (2002)
Khludova, M.: On-line Parallelizable Task Scheduling on Parallel Processors. In: Malyshkin, V. (ed.) PaCT 2013. LNCS, vol. 7979, pp. 229–233. Springer, Heidelberg (2013)
Kleinrock, L.: Queuing Systems, vol. 1. Wiley Interscience (1975)
Grassmann, W.K.: Finding the Right Number of Servers in Real-World Queuing Systems. Interfaces 18(2), 94–104 (1988)
Chase, J., Anderson, D., Thakar, P., Vahdat, A., Doyle, R.: Managing energy and server resources in hosting centers. In: Proceedings of the Eighteenth ACM Symposium on Operating Systems Principles (SOSP), pp. 103–116 (2001)
Bozhokin, S.V.: Wavelet analysis of learning and forgetting of photostimulation rhythms for a nonstationary electroencephalogram. Technical Physics 55(9), 1248–1256 (2010)
George, J.M., Harrison, J.M.: Dynamic control of a queue with adjustable service rate. Operations Research 49, 720–731 (2001)
Mazalov, V.V., Gurtov, A.: Queuing System with On-Demand Number of Servers. Mathematica Applicanda 40(2), 1–12 (2012)
Koole, G., Mandelbaum, A.: Queueing models of call centers: An introduction. Annals of Operations Research 113(1), 41–59 (2002)
Kwon, D., Ko, K., Vannucci, M., Reddy, A., Kim, S.: Wavelet methods for the detection of anomalies and their application to network traffic analysis. Quality and Reliability Engineering International 22(8), 953–969 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Khludova, M. (2014). Resource Allocation Policies for Smart Energy Efficiency in Data Centers. In: Balandin, S., Andreev, S., Koucheryavy, Y. (eds) Internet of Things, Smart Spaces, and Next Generation Networks and Systems. NEW2AN 2014. Lecture Notes in Computer Science, vol 8638. Springer, Cham. https://doi.org/10.1007/978-3-319-10353-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-10353-2_2
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10352-5
Online ISBN: 978-3-319-10353-2
eBook Packages: Computer ScienceComputer Science (R0)