On dimensioning Cloud-RAN systems
Veronica Quintuna Rodriguez, Fabrice M. Guillemin · 2017
We investigate in this paper the implementation of a Cloud-RAN architecture, where several software-based Base Band Units (BBUs) are collocated in a cloud data center. We specifically study several scheduling strategies in order to accelerate the runtime of virtualized BBU functions, and thus, to increase the span of a Cloud-RAN system, given that there are fixed deadlines for the execution of these functions. The main goal of this work is to obtain a simple model for dimensioning a Cloud-RAN infrastructure. For this purpose, we introduce the M[X]/M/C model to capture the behavior of a BBU-pool running on a multi-core platform. The theoretical approach is validated by simulation when performing a Cloud-RAN system hosting one hundred of base stations.