Relay Selection for UAV-Assisted Urban Vehicular Ad Hoc Networks

This letter investigates the relay selection problem for the air-to-ground vehicular ad hoc networks (A2G VANETs). Specifically, we use unmanned aerial vehicle (UAV) to enhance VANETs communications and network performance. For the considered network, we calculate the state transition probability (STP) of communication interruption and the transmission consumption (TC) including energy consumption and delay consumption. Afterward, we formulate the relay selection problem as a multi-objective optimization problem by jointly considering the STP and the TC. For tackling this hard problem, we simplify the primal problem by setting the STP threshold and devise a relay selection algorithm with low complexity through Q-learning. Finally, the simulation results exhibit the performance improvement of our algorithm against other schemes in terms of delivery ratio, delivery latency, and signaling overhead.