Stochastic Bounding Models for Performance Analysis of Clouds

We propose to evaluate the performance of a cloud node (data center) using hysteresis queueing systems and stochastic bound methods. We represent the dynamic behavior of the cloud node by a hysteresis queueing system with forward and backward threshold vectors. The client requests (or jobs) are represented by bulk arrivals entering the buffer, and executed by Virtual Machines (VMs) which are activated and deactivated according to the occupation of the queue, and the threshold sequences. As the system is quite difficult to analyze, we propose to define different bounding systems "less complex" and easier to study. Two approaches are used, one by aggregating the probability distribution of the batch arrivals and another by taking models with the same sequences of forward and backward thresholds. We show the relevance of the proposed bounding systems by presenting some numerical results for the performance measures of a data center.