Deep Reinforcement Learning for Secrecy Energy-Efficient UAV Communication with Reconfigurable Intelligent Surface
Dagiuklas, A. (2023). Deep Reinforcement Learning for Secrecy Energy-Efficient UAV Communication with Reconfigurable Intelligent Surface. IEEE WCNC. Scotland 26 - 29 Mar 2023 Institute of Electrical and Electronics Engineers (IEEE).
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.
|Keywords||Secrecy energy efficiency, deep reinforcement learning, physical layer security, reconfigurable intelligent surface, unmanned aerial vehicle|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Web address (URL)||https://wcnc2023.ieee-wcnc.org/|
|Accepted author manuscript|
File Access Level
|26 Mar 2023|
|Publication process dates|
|Deposited||08 Feb 2023|
|Accepted||08 Jan 2023|
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be
Accepted author manuscript
18views this month
0downloads this month