Litcius/Paper detail

Deep Reinforcement Learning for Secrecy Energy- Efficient UAV Communication with Reconfigurable Intelligent Surface

Mau‐Luen Tham, Yi Jie Wong, Amjad Iqbal, Nordin Ramli, Yongxu Zhu, Tasos Dagiuklas

202352 citationsDOI

Abstract

This paper investigates the physical layer security (PLS) issue in reconfigurable intelligent surface (RIS) aided millimeter-wave rotary-wing unmanned aerial vehicle (UAV) communications under the presence of multiple eavesdroppers and imperfect channel state information (CSI). The goal is to maximize the worst-case secrecy energy efficiency (SEE) of UAV via a joint optimization of flight trajectory, UAV active beamforming and RIS passive beamforming. By interacting with the dynamically changing UAV environment, real-time decision making per time slot is possible via deep reinforcement learning (DRL). To decouple the continuous optimization variables, we introduce a twin- twin-delayed deep deterministic policy gradient (TTD3) to maximize the expected cumulative reward, which is linked to SEE enhancement. Simulation results confirm that the proposed method achieves greater secrecy energy savings than the traditional twin-deep deterministic policy gradient DRL (TDDRL)-based method.

Topics & Concepts

Reinforcement learningComputer scienceBeamformingChannel (broadcasting)Efficient energy useEnergy (signal processing)TrajectoryReal-time computingArtificial intelligenceComputer networkEngineeringTelecommunicationsElectrical engineeringStatisticsMathematicsAstronomyPhysicsAdvanced Wireless Communication TechnologiesUAV Applications and OptimizationWireless Communication Security Techniques