Data analytics based origin-destination core traffic modelling

Traffic monitoring is an essential task for network operators since it allows evaluating network performance. Monitoring data from origin-destination (OD) traffic in core virtual network topologies can be collected from packet nodes and stored in a repository for further analysis, e.g., to detect anomalies or to create predicted traffic matrices for the near future. In this paper we propose a set of modules to support data analytics-based algorithms along with a machine learning procedure based on artificial neural networks (ANN) that provides robust and adaptive traffic models.