Analysis of Cumulative Distribution Function of the Response Time in Cloud Computing Systems with Dynamic Scaling
- 21 Downloads
One of the key performance measures of cloud computing systems is the response time. However, the mean value of this characteristic does not give the full picture of quality of service. Therefore, we derive the cumulative distribution function (CDF) of the response time in terms of Laplace-Stieltjes transform and use it to evaluate moments of the response time. Moreover, we introduce a simplification of the mathematical model that significantly reduces computing complexity for the response time CDF and provide analysis of approximation accuracy of the simplified model.
Keywordscloud computing dynamic scaling hysteretic control queuing system response time
Unable to display preview. Download preview PDF.
- 1.ETSI Cloud Standards Coordination. Final Report 2013, ver. 1.0. http://www.etsi.org/images/files/Events/ 2013/2013_CSC_Delivery_WS/CSC-Final_report-013-CSC_Final_report_v1_0_PDF_format-.PDF. Accessed March 12, 2015.Google Scholar
- 4.Basharin, G.P., Gaidamaka, Yu.V., and Samuilov, K.E., Mathematical teletraffic theory and its application to the analysis of the next generations multiservice networks, Autom. Control Comput. Sci., 2013, vol. 47, no. 2, pp. 11–21.Google Scholar
- 6.Gaidamaka, Yu.V., Pechinkin, A.V., Razumchik, R.V., Samuilov, A.K., Samuilov, K.E., Sokolov, I.A., Sopin, E.S., and Shorgin, S.Ya., The distribution of the return time from the set of overload states to the set of normal load states in a system M | M | 1 | <L,H> | <H,R> with hysteretic load control, Inf. Its Appl., 2013, vol. 7, no. 4, 2013, pp. 20–33.Google Scholar
- 7.Goswami, V., Patra, S.S., and Mund, G.B., Performance analysis of cloud with queue-dependent virtual machines, Proc. of 1st Int’l Conf. on Recent Advances in Information Technology, Dhanbad, 2012, pp. 357–362.Google Scholar
- 10.Lin, M., Wierman, A., Andrew, L.L.H., and Thereska, E., Dynamic right-sizing for power-proportional data centers, INFOCOM, Proceedings IEEE, 2011, pp. 1098–1106.Google Scholar
- 12.Miyoshi, A., Lefurgy, C., Hensbergen, E.V., Rajamony, R., and Rajkumar, R., Critical power slope: Understanding the runtime effects of frequency scaling, Proceedings of the 16th Annual ACM International Conference on Supercomputing, 2002, pp. 35–44.Google Scholar
- 13.Mokrov, E.V. and Chukarin, A.V., Performance analysis of cloud computing system with live migration, T-Comm— Telecommun. Transp., 2014, vol. 8, no. 8, pp. 64–67.Google Scholar
- 14.Mokrov, E.V. and Samouylov, K.E., Modeling of cloud computing as a queuing system with batch arrivals, T-Comm— Telecommun. Transp., 2013, no. 11, pp. 139–141.Google Scholar
- 15.Shorgin, S.Y., Pechinkin, A.V., Samouylov, K.E., Gaidamaka, Y.V., Gudkova, I.A., and Sopin, E.S., Threshold-based queuing system for performance analysis of cloud computing system with dynamic scaling, Proc. of the 12th International Conference of Numerical Analysis and Applied Mathematics ICNAAM-2014, Rhodes, Greece, 2014, United States: AIP Publishing, 2015, vol. 1648, pp. 1–3.Google Scholar
- 16.Gaidamaka, Yu.V., Sopin, E.S., and Talanova, M., Approach to the analysis of probability measures of cloud computing systems with dynamic scaling, Commun. Comput. Inf. Sci., 2016, vol. 601, pp. 121–131.Google Scholar
- 17.Wu, Q., Juang, P., Martonosi, M., Peh, L.-S., and Clark, D.W., Formal control techniques for power performance management, IEEE Micro, 2005, vol. 25, pp. 52–62.Google Scholar