Modeling of the minimum number of nodes of a private university cloud virtualization cluster

Abstract

Cloud technologies and computing have long been part of the practice of leading universities. However, we note that the problem of estimating the optimal number of necessary nodes of a virtualization cluster still remains relevant. When designing the virtual desktop infrastructure (or VDI) of a university private cloud, developers face many technical challenges. One of them is to estimate the minimum required number of virtualization cluster nodes on which users’ virtual machines (VMs) are hosted. These VMs, for example, are used by students and teachers to complete training tasks. Another task that arises in the development of the VDI configuration is the task of algorithmizing the placement of the VM in the computer network (СN) of the university. In this case, the optimal placement of the VM allows you to mini- mize the number of nodes of the aircraft. And this does not affect the functionality of VDI in the sun. This approach will help reduce the cost of a solution for using the infrastructure of a private university cloud. And the latter is important for universities. The article offers a model for estimating the required number of virtualization cluster nodes. The proposed model is based on a combined approach, which involves jointly solving the problem of optimal packaging and finding the configuration of server platforms of a private university cloud using a genetic algorithm.