Energy Efficient Trajectory and Communication Design for NOMA-Enhanced UAV-Assisted IoV

Vehicle road cooperation technology is an important development direction for future intelligent transportation systems, which can provide effective solutions to the safety challenges faced by single-vehicle intelligence. Reliable Vehicle-to-Infrastructure (V2I) communication is a guarantee to support real-time interaction between vehicular user equipments (VUEs) and Road Side Units (RSUs). To enhance the flexibility and efficiency of V2I communication, we propose a Non-Orthogonal Multiple Access (NOMA)-enhanced Unmanned Aerial Vehicle (UAV)-assisted data transmission scheme for the Internet of Vehicles (IoV), in which the UAV serves as a relay to forward the RSU data required by VUEs. In particular, this scheme considers a NOMA-enhanced relay forwarding method and the non-cooperative vehicle-to-vehicle communication. To fully exploit the advantages of the proposed scheme, we propose a joint optimization problem involving user scheduling, UAV trajectory, and UAV transmission power with the objective of improving system energy efficiency. To cope with the demand for high network optimization efficiency due to rapid topology changes in IoV, we design a deep reinforcement learning algorithm based on prioritized experience replay-deep deterministic policy gradient, which can efficiently provide reliable solutions. Extensive simulation results are provided to corroborate the effectiveness of the proposed method.