Efficient resource prediction framework for software-defined heterogeneous radio environmental infrastructures

Artificial Intelligence (AI) is defining the future of next-generation infrastructures as proactive and data-driven systems. AI-empowered radio systems are replacing the existing command and control radio networks due to their intelligence and capabilities to adapt to the radio environmental infrastructures that include intelligent networks, smart cities and AV/VR enabled factory premises or localities. An efficient resource prediction framework (ERPF) is proposed to provide proactive knowledge about the availability of radio resources in such software-defined heterogeneous radio environmental infrastructures (SD-HREIs). That prior information enables the coexistence of radio users in SD-HREIs. In a proposed framework, the radio activity is measured in both the unlicensed bands that include 2.4 and 5 GHz, respectively. The clustering algorithms k- means and DBSCAN are implemented to segregate the already measured radioactivity as signal (radio occupancy) and noise (radio opportunity). Machine learning techniques CNN and LRN are then trained and tested using the segregated data to predict the radio occupancy and radio opportunity in SD-HREIs. Finally, the performance of CNN and LRN is validated using the cross-validation metrics.