Sub-Connected Active RIS-Assisted UAV Communications: A DRL Approach for Joint Trajectory and Power Optimization
Year: 2026
Type: article
Abstract: Unmanned aerial vehicle (UAV) communications offer flexible coverage in urban environments but suffer from severe path loss and stringent energy constraints. Although active reconfigurable intelligent surface (RIS) technology can mitigate the double fading effect through signal amplification, fully-connected architectures impose prohibitive hardware costs and power overhead on resource-constrained UAV platforms. To address this, we propose a sub-connected active RIS-assisted UAV communication system, where multiple reflecting elements share a single amplifier to balance performance and implementation complexity. We formulate an energy efficiency maximization problem that jointly optimizes UAV trajectory, RIS phase shifts and amplitude coefficients, and transmit power allocation under quality-of-service constraints. The problem is cast as a Markov decision process and solved via a twin delayed deep deterministic policy gradient (TD3) algorithm. Numerical results demonstrate that the proposed sub-connected architecture achieves 9.6% higher energy efficiency than the fully-connected design, while its total power consumption increases by only 4.6% across the full rate operating range, and the TD3-based framework outperforms the Deep Deterministic Policy Gradient (DDPG) baseline by 19.1% in energy efficiency. These results validate the effectiveness and practicality of the proposed system for energy-efficient UAV communications.
Institution: Qufu Normal University
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,645
OpenAlex ID: W7204904420