Energy Consumption x Quality of Service in Data Centers
Abstract
Several recent works reduce energy consumption in data centers but consider one or two of the three highest consumption dimensions, i.e., servers, cooling system, and network infrastructure. However, algorithms that optimize only one or two of those dimensions may hide significant energy losses in the other dimensions. Moreover, energy-saving strategies may increase service response times and violate service level agreements. This paper presents an extensive study of the relations between the three dimensions of higher-energy consumption in a data center and their impact on parameters of quality of service. The paper also proposes an algorithm for allocating virtual machines that exploit varying load levels in the data center to save energy more aggressively or to minimize violations of service level agreements and presents a new simulator for studying energy efficiency of data centers that allows the evaluation of several scheduling algorithms under different workloads, cooling strategies, and network optimizations. The experimental results are from more than 500 simulations with three traces of real workloads with up to 696 thousand virtual machines running over a period of up to 34 days.
References
Beloglazov, A. and Buyya, R. (2012). Optimal Online Deterministic Algorithms and Adaptive Heuristics for Energy and Performance Efficient Dynamic Consolidation of Virtual Machines in Cloud Data Centers. Concurrency and Computation: Practice and Experience, 24(13):1397–1420.
Benson, T., Anand, A., Akella, A., and Zhang, M. (2010). Understanding Data Center Traffic Characteristics. SIGCOMM Comput. Commun. Rev., 40:92–99.
Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., and Buyya, R. (2011). CloudSim: A Toolkit for Modeling and Simulation of Cloud Computing Environments and Evaluation of Resource Provisioning Algorithms. Software: Practice and Experience, 41(1):23–50.
GARTNER (2018). The Data Center Is Dead, and Digital Infrastructures Emerge. https://www.equinix.com.br/resources/analyst-reports/gartner-emerging-digital-infrastructures/.
Ge, C., Sun, Z., and Wang, N. (2013). A Survey of Power-Saving Techniques on Data Centers and Content Delivery Networks. IEEE Communications Surveys Tutorials, 15(3):1334–1354.
Hebrew (2018). Parallel Workloads Archive. https://www.cs.huji.ac.il/labs/parallel/workload/logs.html.
Heller, B., Seetharaman, S., Mahadevan, P., Yiakoumis, Y., Sharma, P., Banerjee, S., and McKeown, N. (2010). ElasticTree: Saving Energy in Data Center Networks. In Proceedings of the 7th USENIX NSDI, NSDI’10, pages 17–17, Berkeley, CA, USA. USENIX Association.
Kliazovich, D., Bouvry, P., and Khan, S. (2012). GreenCloud: A Packet-Level Simulator of Energy-Aware Cloud Computing Data Centers. The Journal of Supercomputing, 62(3):1263–1283.
Moore, J., Chase, J., Ranganathan, P., and Sharma, R. (2005). Making Scheduling Cool: Temperature- Aware Workload Placement in Data Centers. In Proceedings of The USENIX Annual Technical Conference, ATC ’05, pages 5–5, Berkeley, CA, USA. USENIX Association.
Moro, M. P. (2018). SimDC3D: A Data Center Simulator. https://github.com/simdc3d.
Nucci, A., Sridharan, A., and Taft, N. (2005). The Problem of Synthetically Generating IP Traffic Matrices: Initial Recommendations. SIGCOMM Comput. Commun. Rev., 35(3):19–32.
Rainer Hegger, Holger Kantz, T. S. (2016). TISEAN 3.0.1 - Nonlinear Time Series Analysis. http://http://www.mpipks-dresden.mpg.de/ tisean/.
Ricciardi, S., Careglio, D., Santos-Boada, G., Sole-Pareta, J., Fiore, U., and Palmieri, F. (2011). Saving Energy in Data Center Infrastructures. In Data Compression, Communications and Processing (CCP), 2011 First International Conference on, pages 265–270.
Rong, H., Zhang, H., Xiao, S., Li, C., and Hu, C. (2016). Optimizing Energy Consumption for Data Centers. Renewable and Sustainable Energy Reviews, 58(C):674–691.
Saino, L., Cocora, C., and Pavlou, G. (2013). A Toolchain for Simplifying Network Simulation Setup. In Proceedings of the 6th International ICST Conference on Simulation Tools and Techniques, SIMUTOOLS ’13, ICST, Brussels, Belgium, Belgium. ICST.
Tighe, M., Keller, G., Bauer, M., and Lutfiyya, H. (2012). DCSim: A Data Centre Simulation Tool for Evaluating Dynamic Virtualized Resource Management. In CNSM 2012 Workshop on Systems Virtualiztion Management, pages 385–392.
Yeo, S. and Lee, H.-H. S. (2012). SimWare: A Holistic Warehouse-Scale Computer Simulator. Computer, 45(9):48–55.
Yue, M. and Zhang, L. (1995). A Simple Proof of the Inequality MFFD(L) <= 71/60 OPT(L) + 1, L for the MFFD Bin-Packing Algorithm. Acta Mathematicae Applicatae Sinica, 11(3):318–330.
