The 5G PPP Working group on Network Management and QoS issued a position paper on “Cognitive Network Management for 5G” and asked for inputs.
The final version is now available. Views sent through the online consultation have been integrated.
5G represents a complete revolution of mobile networks for accommodating the over-growing demands of users, services and application. In contrast to previous transitions between mobile networks generations, in 5G there will be a much complex management requirements based on the softwarization of network resources. This ultimately will lead to a system that requires realtime management based on a hierarchy of complex decision making techniques that analyse historical, temporal and frequency network data. Cognitive network management has been proposed as the current solution for this problem, in which the use of machine learning to develop self-aware, self-configuring, self-optimization, self-healing and self-protecting systems will enable cognitive network management. This technology is needed for managing a demanding infrastructure but one that yet has to present scalability and flexibility, such as that needed in 5G. In this paper, the novelties for network management in 5G are presented, including: autonomicity, NFV, SDN, network slicing, architectures, security and KPIs.
All these points are also explained in the context of the current development of network management solutions within the 5GPPP phase 1 projects, including: CogNet, Selfnet, SONATA and 5GeX. The Selfnet management architecture and its possibilities for efficient self-organized network management for 5G based on virtualized and software defined networks have been specifically described. The development of such novelties will pave the way for not only the future of cognitive network management, but for 5G and also the future mobile network generations.
Do not miss it and have a look here!