Joint Deployment, Power Control, and Beamforming Designs for Movable Antenna-Aided UAV Communication: A DRL-Based Two-Stage Approach

Movable antenna (MA) technology enables flexible beamforming through adaptive adjustment of antenna positions, thereby enhancing communication performance. This paper investigates the MA-aided air-to-ground (A2G) system, where an unmanned aerial vehicle (UAV) equipped with MAs serves multiple ground users. The primary objective is to jointly optimize UAV deployment, antenna positions, beamforming, and power control to maximize the downlink communication sum rate. A key challenge lies in the difficulty of acquiring complete instantaneous channel state information (I-CSI), as the antennas cannot traverse all possible positions to obtain such full-scale I-CSI, which impedes the efficient optimization of system parameters. To address this challenge, we propose a two-stage transmission scheme: in the first stage, location-aware statistical CSI (S-CSI) is leveraged to optimize UAV deployment, power control, and MA positions for maximizing long-term system performance, while the second stage estimates I-CSI based on the optimized UAV and antenna positions to refine short-term transmit beamforming after long-term variables are determined, thereby substantially reducing CSI acquisition overhead. For long-term policy optimization, we introduce a novel dual-spatial-scale hierarchical deep reinforcement learning (DSSH-DRL) framework, which preserves flexibility in global policy formulation while enhancing training efficiency via effective decoupling of control variables. Simulation results demonstrate the effectiveness of the proposed algorithm and validate the promising application potential of MA technology in A2G communication networks.