Beam-Steering Optimization in Multi-UAVs mmWave Networks: A Mean Field Game Approach

In unmanned aerial vehicle (UAV)-assisted mmWave networks, the beam-steering issue is a significant challenge to establish the reliable and steady connection between flying base stations and ground users. In this paper, we investigate the optimization problem of beam-steering in the multi-UAVs and multi-antennas mmWave (MUMA) networks to maximize the system sum-rate by adjusting each beam-steering angle of departure. In order to solve this problem, we propose a novel mean field game (MFG)-based massive multi-input multi-output (MIMO) angle control algorithm to obtain the optimal mmWave channel allocation between UAVs and ground users. In addition, when dealing with the problem of initial sensitivity and difficulty in solving the partial differential equations in the MFG, we utilize reinforcement learning to achieve the mean field equilibrium. Simulation results show the proposed algorithm can improve the system sum-rate with a faster convergence, verifying the efficiency of the proposed algorithm.