Machine Learning-Based Service Differentiation in the 5G Core Network

The proliferation of network virtualization, cloud computing, and software-defined networking have made a significant impact on how mobile networks are designed and operated. Much of this advancement can stand to gain from the incorporation of intelligent network management techniques such as those offered by Machine Learning. The increase in the amount of traffic with varying QoS requirements places an enormous challenge on end-to-end service provisioning and delivery. Network management required from providing support for service differentiation is one of the key pillars of 5G and beyond networks. In this paper, we present the design and implementation of a user traffic optimization framework that is based on the classification of network traffic of individual users. We also present the design and implementation of a network operations management framework, that is based on the usage of real mobile network usage data sets.