Virtual network topology adaptability based on data analytics for traffic prediction

The introduction of new services requiring large and dynamic bitrate connectivity can cause changes in the direction of the traffic in metro and even core network segments throughout the day. This leads to large overprovisioning in statically managed virtual network topologies (VNTs), which are designed to cope with the traffic forecast. To reduce expenses while ensuring the required grade of service, in this paper we propose a VNT reconfiguration approach based on data analytics for traffic prediction (VENTURE). It regularly reconfigures the VNT based on the predicted traffic, thus adapting the topology to both the current and the predicted traffic volume and direction. A machine learning algorithm based on an artificial neural network is used to provide robust and adaptive traffic models. The reconfiguration problem that takes as its input the traffic prediction is modeled mathematically, and a heuristic is proposed to solve it in practical times. To support VENTURE, we propose an architecture that allows collecting and storing data from monitoring at the routers and that is used to train predictive models for every origin-destination pair. Exhaustive simulation results of the algorithm, together with the experimental assessment of the proposed architecture, are finally presented.