SliceNet has recently proceeded with the design and implementation of a 5G RAN-Core slicing-friendly infrastructure supporting control and data plane programmability based on the FlexRAN and LL-MEC Mosaic5G platforms on top of the OAI RAN and OAI CN deployment. Ongoing work includes the design and prototype implementation of a RAN monitoring framework extension over FlexRAN that will provide raw material to QoE monitoring and machine learning-based models for resource optimization.
There are two network cognition strands: first, an integrated methodology approach to cognitive network & slice management for designing, implementing and running cognitive models; second, on the aspects of cognitive control to support QoS/QoE in RAN slicing.