Be Scalable and Rescue My Slices During Reconfiguration

Modern 5G networks promise more bandwidth, less delay, and more flexibility for an ever increasing number of users and applications, with Software Defined Networking, Network Function Virtualization, and Network Slicing as key enablers. Within that context, efficiently provisioning network and cloud resources of a wide variety of applications with dynamic users' demands is a real challenge. In this work, we consider the problem of network slice reconfiguration. Reconfiguring from time to time network slices allows to reduce the network operational costs and to increase the number of slices that can be managed within the network. However, it impacts users' Quality of Service during the reconfiguration step. To solve this issue, we study solutions implementing a make-before-break scheme. We propose new models and scalable algorithms (relying on column generation techniques) that solve large data instances in few seconds.