Evaluating Performance of Active Containers on PaaS Fog under Batch Arrivals: A Modeling Approach

Model-based performance evaluation of large-scale PaaS Fog Datacenter requires to develop a hierarchical model, which is usually composed of a series of monolithic models. This paper proposes an approximate analytic modeling approach to evaluate the performance of a pool of active containers on a PaaS Fog physical node under batch task arrivals, by using an $M^{[\mathrm{x}]}/G/m/m+K$ queue. We describe the details of the proposed model and the formulas for calculating performance measures of interest. Experiment results indicate that the proposed approach (including the model and the formulas) can approximately capture the system behaviors even when the task service-time distribution has a large coefficient of variation (>1.5).