Configuring Cloud Admission Policies under Dynamic Demand

• Published in: 2013 IEEE 21st International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems pp. 313 - 317
• Main Authors: Unuvar, Merve, Doganata, Yurdaer N., Tantawi, Asser N.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.08.2013
• Subjects: Admission control; Approximation; Cloud computing; cloud management; Computer simulation; Demand; dynamic resource demand; Dynamic scheduling; Electric communication systems; Mathematical models; performance comparison; Policies; Probabilistic logic; Probability density function; Probability distribution; Rejection; Resource management; virtual machines
• ISSN: 1526-7539; 2375-0227
• DOI: 10.1109/MASCOTS.2013.42

We consider the problem of admitting sets of, possibly heterogenous, virtual machines (VMs) with stochastic resource demands onto physical machines (PMs) in a Cloud environment. The objective is to achieve a specified quality-of-service related to the probability of resource over-utilization in an uncertain loading condition, while minimizing the rejection probability of VM requests. We introduce a method which relies on approximating the probability distribution of the total resource demand on PMs and estimating the probability of over-utilization. We compare our method to two simple admission policies: admission based on maximum demand and admission based on average demand. We investigate the efficiency of the results of using our method on a simulated Cloud environment where we analyze the effects of various parameters (commitment factor, coefficient of variation etc.) on the solution for highly variate demands.