Study and evaluation of QoS degradation costs in optical-nfv network environments with resource allocations based on long short term memory prediction techniques

The paper investigates the effectiveness of bandwidth prediction technique based on Long Short Term Memory recurrent neural networks for the resource allocation in Network Function Virtualization network architectures in which the datacenters are interconnected by an Elastic Optical Network. In particular we evaluate the under-provisioning costs that occurs when fewer resources than the needed ones are allocated and characterizes the QoS penalty cost to be paid by the provider because of the QoS degradation.