Abstract
This article investigates a secure aerial reconfigurable intelligent surface (A-RIS) communication system, where user mobility, imperfect channel state information (CSI), and RIS phase errors induced by uncrewed aerial vehicle (UAV) jitter significantly degrade performance. To address these challenges, we formulate a joint optimization problem for UAV trajectory, base station (BS) we propose abeamforming, and A-RIS beamforming to maximize the minimum secrecy energy efficiency (SEE), subject to constraints on user secrecy rates and UAV energy efficiency. To solve this highly non-convex problem, we propose a novel reinforcement learning framework termed IA-CSORL based on the twin-twin-delayed deep deterministic policy gradient (TTD3) architecture, which incorporates two novel modules. Specifically, we develop the phase-aware relativistic adaptive descent (PRAD) algorithm is proposed, which embeds the learning process into a conformal Hamiltonian system. By integrating gradient-based phase error correction and adaptive momentum adjustment, PRAD effectively counteracts phase noise and stabilizes training. Furthermore, we design an environment-state interactive attention (ESIA) mechanism to dynamically fuse UAV positioning and environmental features, enhancing state representation and deployment accuracy. Numerical results demonstrate that IA-CSORL significantly outperforms existing RL baselines in terms of both robustness and convergence performance. Moreover, IA-CSORL achieves superior beamforming accuracy under phase errors and CSI imperfections and provides a better trade-off between sum secrecy rate (SSR) and SEE, with performance gains becoming more significant as the number of RIS elements increases.
Funding Information
  • National Natural Science Foundation of China (62501184)
  • National Natural Science Foundation of China (U23A20271)
  • National Natural Science Foundation of China (62501184)
  • European Union through the Horizon Europe Project COVER (101086228)
  • Horizon Europe Project UNITE (101129618)
  • Horizon Europe Project INSTINCT (101139161)
  • Horizon Europe project TWIN6G (101182794)
  • Agence Nationale de la Recherche through the France 2030 Project ANR-PEPR Networks of the Future (YACARI 22-PEFT-0005)
  • CHIST-ERA Project PASSIONATE (CHIST-ERA-22-WAI-04)
  • CHIST-ERA Project PASSIONATE (ANR-23-CHR4-0003-01)
  • Engineering and Physical Sciences Research Council
  • UK Research and Innovation, in part by the UK Department of Science, Innovation and Technology (EP/X040518/1)
  • UK Research and Innovation, in part by the UK Department of Science, Innovation and Technology (EP/Y037421/1)
  • HASC Telecom Hub (EP/X040569/1)

This publication has 51 references indexed in Scilit: