Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Energy Efficient RSMA-Based LEO Satellite Communications Assisted by UAV-Mounted BD-Active RIS: A DRL Approach

Rahman Saadat Yeganeh, Hamid Behroozi

TL;DR

The paper tackles energy-efficient optimization for a RSMA-enabled non-terrestrial network where a UAV-mounted BD-ARIS assists LEO-satellite downlinks to multiple ground users. It formulates a non-convex EE objective over beamforming, RIS configuration, rate-splitting, and UAV placement and solves it with three DRL algorithms—TD3, A3C, and TRPO—incorporating realistic power models and imperfect CSI. Across extensive simulations, TRPO consistently delivers the best EE and stability, with BD-ARIS outperforming conventional RIS architectures and RSMA outperforming NOMA in high-antenna and large-RIS regimes. The work demonstrates scalable, energy-efficient design principles for future 6G NTN deployments and IoT applications, highlighting the value of combining RSMA with actively controlled RIS and robust DRL-based optimization.

Abstract

This paper proposes an advanced non-terrestrial communication architecture that integrates Rate-Splitting Multiple Access (RSMA) with a Beyond-Diagonal Active Reconfigurable Intelligent Surface (BD-ARIS) mounted on a UAV under the coverage of a Low Earth Orbit (LEO) satellite. The BD-ARIS adopts a group-connected structure to enhance signal amplification and adaptability, while RSMA enables efficient multi-user access by dividing messages into common and private components. The system jointly optimizes satellite beamforming, UAV positioning, power allocation, and rate-splitting ratios to maximize the overall energy efficiency (EE). To solve the resulting non-convex and high-dimensional problem, we employ three state-of-the-art deep reinforcement learning (DRL) algorithms: Trust Region Policy Optimization (TRPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Asynchronous Advantage Actor-Critic (A3C). Moreover, realistic models for the power consumption of both the UAV and the BD-ARIS are considered. Simulation results reveal that TRPO consistently achieves the best performance in terms of EE and sum rate, especially under high transmit powers and challenging deployment scenarios. TD3 converges faster and performs competitively in moderate settings, while A3C suffers from instability due to its high variance. Additionally, the robustness of each algorithm under channel state information (CSI) uncertainty is evaluated, confirming TRPO resilience to imperfect observations. Overall, the proposed RSMA-BD-ARIS framework significantly outperforms conventional RIS-assisted designs and provides a scalable, energy-efficient solution for 6G and massive IoT applications in non-terrestrial networks.

Energy Efficient RSMA-Based LEO Satellite Communications Assisted by UAV-Mounted BD-Active RIS: A DRL Approach

TL;DR

The paper tackles energy-efficient optimization for a RSMA-enabled non-terrestrial network where a UAV-mounted BD-ARIS assists LEO-satellite downlinks to multiple ground users. It formulates a non-convex EE objective over beamforming, RIS configuration, rate-splitting, and UAV placement and solves it with three DRL algorithms—TD3, A3C, and TRPO—incorporating realistic power models and imperfect CSI. Across extensive simulations, TRPO consistently delivers the best EE and stability, with BD-ARIS outperforming conventional RIS architectures and RSMA outperforming NOMA in high-antenna and large-RIS regimes. The work demonstrates scalable, energy-efficient design principles for future 6G NTN deployments and IoT applications, highlighting the value of combining RSMA with actively controlled RIS and robust DRL-based optimization.

Abstract

This paper proposes an advanced non-terrestrial communication architecture that integrates Rate-Splitting Multiple Access (RSMA) with a Beyond-Diagonal Active Reconfigurable Intelligent Surface (BD-ARIS) mounted on a UAV under the coverage of a Low Earth Orbit (LEO) satellite. The BD-ARIS adopts a group-connected structure to enhance signal amplification and adaptability, while RSMA enables efficient multi-user access by dividing messages into common and private components. The system jointly optimizes satellite beamforming, UAV positioning, power allocation, and rate-splitting ratios to maximize the overall energy efficiency (EE). To solve the resulting non-convex and high-dimensional problem, we employ three state-of-the-art deep reinforcement learning (DRL) algorithms: Trust Region Policy Optimization (TRPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Asynchronous Advantage Actor-Critic (A3C). Moreover, realistic models for the power consumption of both the UAV and the BD-ARIS are considered. Simulation results reveal that TRPO consistently achieves the best performance in terms of EE and sum rate, especially under high transmit powers and challenging deployment scenarios. TD3 converges faster and performs competitively in moderate settings, while A3C suffers from instability due to its high variance. Additionally, the robustness of each algorithm under channel state information (CSI) uncertainty is evaluated, confirming TRPO resilience to imperfect observations. Overall, the proposed RSMA-BD-ARIS framework significantly outperforms conventional RIS-assisted designs and provides a scalable, energy-efficient solution for 6G and massive IoT applications in non-terrestrial networks.
Paper Structure (36 sections, 40 equations, 8 figures, 2 tables, 3 algorithms)

This paper contains 36 sections, 40 equations, 8 figures, 2 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Background
  3. Related Works
  4. Contributions
  5. System Model
  6. Channel Model
  7. BD-Active RIS with Group-Connected Architecture
  8. Transmission Protocol
  9. Power Consumption Model
  10. Power Consumption of BD-Active RIS
  11. Hovering Power Consumption Model for Rotary-Wing UAVs
  12. Problem Formulation
  13. Deep Reinforcement Learning
  14. Markov Decision Process (MDP)
  15. State
  16. ...and 21 more sections

Figures (8)

  • Figure 1: System model of a UAV-mounted BD-ARIS-assisted LEO satellite communication network with multiple ground users.
  • Figure 2: Training reward comparison of TD3, A3C, and TRPO in BD-ARIS-assisted RSMA network.
  • Figure 3: Energy efficiency of the RSMA-based system under different DRL algorithms: (a) vs. satellite transmit power, (b) vs. BD-ARIS transmit power.
  • Figure 4: Sum rate vs. vertical distance between UAV-mounted BD-ARIS and ground users.
  • Figure 5: Communication reliability vs. CSI error variance $\sigma_{\mathbf{X}}^2$ under TD3, A3C, and TRPO. The case $\sigma_{\mathbf{X}}^2 = 10^{-4}$ approximates perfect CSI.
  • ...and 3 more figures