Cognative Network Management for 5G

A consultation paper from the  5GPPP Working Group on Network Management and QoS

Download the Network Management whitepaper 1-0 here.

5G Network Management is a non-trivial endeavour which faces a host of new challenges beyond 3G and 4G. The number of nodes, the homogeneity of the access technologies, the conflicting management objectives, resource usage minimization, and the division between limited physical resources and elastic virtual resources is driving a complete change in the methodology for efficient network management.

In the past, a distinction was typically made between the control and data plane of the network. However the model of the 5G network can be expanded to also be considered in terms of a Service and Softwarisation plane, where the management of the network services and the virtualised devices is an integral part of the overall network. This model can be used for extending the idea of network management to the reliance on an increased overall capacity of computational resources to create a robust solution.

Historically, autonomic management has gone as far as developing complete automated solutions into the network. The concept of “the selves” was introduced, in which network management is expressed through a mixture of the approaches including: self-awareness, self-configuration, self-optimization, self-healing and self-protection. With the advancements of the infrastructure technology for accommodating the next generation of networks, the next level of network management has to incorporate the flexible manipulation of network resources and leverage it with the number of users, the network traffic, the SLAs, and the demanded system performance. Fig 1 presents the vision of this paper, which is elevating the level of cognitive abilities in the “selves“ using machine learning. Machine learning has the capability of adapting an entire system based on historical data, which means in 5G, that the network will fully understand system variables and optimally adjust their values for achieving a superior network configuration. In the end, cognitive network management is introduced as the next generation of network management and key driver of 5G success.

We now like to get your views on our Network Management thoughts before we finalise our position paper.

This consultation is open to all and will accept inputs until the 2oth of December 2016.