Study and Investigation of SARIMA-based Traffic Prediction Models for the Resource Allocation in NFV networks with Elastic Optical Interconnection

The paper investigates resource allocation problems in Network Function Virtualization (NFV) network architectures in which the datacenters are interconnected by an Elastic Optical Network and the offered traffic is predicted by a Seasonal Autoregressive Integrated Moving Average (SARIMA) model. We apply a procedure for deseasonalizing, eliminating the trend, estimating the parameters of the SARIMA model and forecasting real traffic values. The procedure is able to forecast the traffic so as to minimize the network operation cost and taking into account the following cost components: i) the cloud resource costs occurring when a higher resource provisioning is accomplished due to traffic overestimation; ii) the Quality of Service (QoS) degradation cost due to the user traffic loss occurring when the traffic is underestimated and fewer resources than needed are allocated.