5G will realise a true Internet of Things, a network capable of supporting potentially trillions of wireless connected devices and with overall bandwidth one thousand times higher that today's wireless networks. Current 4G technology is approaching the limits of what is possible with this generation of radio technology and to address this, one of the key requirements of 5G will be to create a network that is highly optimised to make maximum use of available radio spectrum and bandwidth for QoS, and because of the network size and number of devices connected, it will be necessary for it to largely manage itself and deal with organisation, configuration, security, and optimisation issues. Virtualisation will also play an important role as the network will need to provision itself dynamically to meet changing demands for resources and Network Function Virtualisation (NFV), the virtualising of network nodes functions and links, will be the key technology for this.

A possible approach is to apply Autonomic Network Management based on Machine Learning as a key technology enabling an (almost) self administering and self managing network. Network software will be capable of forecasting resource demand requirements through usage prediction, recognising error conditions, security conditions, outlier events such as fraud, and responding and taking corrective actions. Energy efficiency will also be a key requirement with the possibility to reconfigure the NFV to for example avail of cheaper or greener energy when it is available and suitable. Again this is directly related to usage prediction both at a macro level, across an entire network, and at a micro level within specific cells.

The 5G-PPP CogNet project will bring advanced Machine Learning concepts and apply these in the domain of Network Management for 5G with the core objective of using the available network and environmental data to improve the operational efficiency of the network and enable the scale and QoS expected in 5G. It will use data collected from Virtualized Network Functions in data centres and also from specific telecoms hardware equipment, classify and filter this data, apply algorithms to create rules and configurations for existing network management applications, and deliver human readable outputs describing the observations and policies. 

Partners: 

• WIT
• Telefonica
• IBM
• VICOMTECH
• INTEROUTE
• Fraunhofer FOKUS
• Technische Universität Berlin
• UPM
• Alcatel
• UNITN
• WeFi