Regret Based Learning for UAV Assisted LTE-U/WiFi Public Safety Networks

Broadband wireless communication is of critical importance during public safety scenarios as it facilitates situational awareness capabilities for first responders and victims. In this paper, the use of LTE-Unlicensed (LTE-U) technology for unmanned aerial base stations (UABSs) is investigated as an effective approach to enhance the achievable broadband throughput during emergency situations by utilizing the unlicensed spectrum. In particular, we develop a game theoretic framework for load balancing between LTE-U UABSs and WiFi access points (APs), based on the users' link qualities as well as the loads at the UABSs and the ground APs. To solve this game, we propose a regret-based learning (RBL) dynamic duty cycle selection (DDCS) method for configuring the transmission gaps in LTE-U UABSs, to ensure a satisfactory throughput for all users. Simulation results show that the proposed RBL-DDCS yields an improvement of 32% over fixed duty cycle LTE-U transmission, and an improvement of 10% over Q-learning based DDCS.