This project will investigate how artificial intelligence can be used in future cloud based radio access networks. Such networks will be typical in future 5G and beyond 5G deployments, where due to cost reasons, radio and processing functions will be more centralised. This brings with it new challenges particularly in efficient capacity assignment and maintaining security in this highly adaptable environment. It is anticipated the Software Defined Networking (SDN) and Network Function Virtualisation (NFV) will be two important aspects. Aspects like multi-tenancy, and the best split in terms of distributed and cloud radio access networks will be considered. The project will investigate how machine learning based cognition strategies can be used to control both the radio resources and network topology, when traffic is dominated by ultra-high definition video from vehicular users. A mixture of simulation and analysis will be used to assess performance. Stochastic Geometry, Game theory and Markov analysis will be particularly important analytical tools.