Opportunistic RL-based WiFi Access for Aerial Sensor Nodes in Smart City Applications

Unmanned air vehicles are becoming widespread, driven by improved wireless technologies. However, the WiFi technology used for communication has a highly crowded and unevenly distributed channel occupancy in its spectrum. To overcome this, WiFi resources need to be utilized efficiently. Therefore, this paper proposes the Opportunistic Reinforcement Learning-based WiFi Access scheme, which exploits intermittent channel occupancy to solve the NP-hard channel assignment problem. As a result, the proposed model has improved the accurate channel selection on the UAVs by 9%, performing 91% accuracy, compared to the trivial channel scoring-based selection algorithms.