Joint Resource Allocation for UAV-Assisted V2X Communication With Mean Field Multi-Agent Reinforcement Learning

The Vehicle-to-Everything (V2X) communication, as the fundamental part of intelligent transport system, has the potential to increase road safety and traffic efficiency. However, conventional static infrastructures like roadside units (RSUs) often encounter overload issues due to the uneven spatiotemporal distribution of vehicles. Although the line-of-sight (LoS) propagation characteristics and high mobility of autonomois aerial vehicles (AAVs) have brought about UAV-assisted vehicular communication. The scarce spectrum resources, complex interference, restricted energy budgets, and the mobility of automobiles still pose significant challenges. In this paper, we combine mean-field game (MFG) theory with multi-agent reinforcement learning (MARL) to allocate resources for RSUs and UAVs in non-orthogonal multiple access (NOMA) V2X communication networks. To find rational and reasonable global solutions for infrastructures under power and QoS constraints, a joint sub-band scheduling and transmit power allocation problem is addressed. The MARL technique is utilized to endow agents with the capability of self-learning. MFG theory is employed to tackle the tremendous overhead in agent interactions. The integration of MFG and MARL enables infrastructures to act as agents, engaging in mutual interactions and considering the impact of the surrounding environment, to achieve maximum global energy efficiency. Simulation results demonstrate the effectiveness of UAV-assisted V2X communication and prove that the proposed method outperforms a state-of-the-art resource allocation scheme in both average energy efficiency and probability of failure.