Intelligent network management mechanisms as a step towards SG

The evolution of telecom networks towards 5G comes with challenges that permeate the entire network structure and its management principles. In this paper, we outline how challenges such as the need to support different types of users and new network business models, the movement towards virtualization, as well as the need for more automation drive the requirement for a holistic and flexible way of managing the networks. We detail the architectural principles that underline such a cognitive management framework and we exemplify its use through a scenario based on software defined networking, where we combine machine learning, control and automation in the context of flexible resource provisioning in the Radio Access Network. Our experiments were conducted in collaboration with a major telecom operator and clearly show the advantages of introducing intelligence and automation into the network.