Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Personalized Federated Reinforcement Learning for RIS-Assisted Aerial Relays in SAGINs with Fluid Antennas

Yuxuan Yang, Bin Lyu, Abbas Jamalipour

TL;DR

This paper investigates a SAGIN in which low Earth orbit (LEO) satellite constellations communicate with multiple ground hotspots via RIS-assisted UAV relays, serving both FAS-equipped and conventional users.

Abstract

Space-air-ground integrated networks (SAGINs) interconnect satellites, uncrewed aerial vehicles (UAVs), and ground devices to enable flexible and ubiquitous wireless services. The integration of reconfigurable intelligent surfaces (RISs) and fluid antenna systems (FASs) further enhances radio environment controllability. However, the tight integration of cross-layer facilities and radio enhancement technologies leads to pronounced environmental dynamics and heterogeneity, posing fundamental challenges for system modeling and optimization in large-scale SAGINs. This paper investigates a SAGIN in which low Earth orbit (LEO) satellite constellations communicate with multiple ground hotspots via RIS-assisted UAV relays, serving both FAS-equipped and conventional users. A system model is developed that explicitly captures satellite mobility, UAV trajectories, RIS phase control, and heterogeneous user reception capabilities. Accordingly, a multi-hotspot downlink rate maximization problem is studied, whose solvability is analyzed through a hierarchical Stackelberg game. To address heterogeneous and time-varying multi-hotspot environments, an adaptive personalized federated reinforcement learning (FRL) algorithm is proposed for adaptive optimization of UAV trajectories and RIS phase controls. Simulation results demonstrate superior performance and validate the effectiveness of personalization in dynamic heterogeneous SAGIN scenarios.

Adaptive Personalized Federated Reinforcement Learning for RIS-Assisted Aerial Relays in SAGINs with Fluid Antennas

TL;DR

This paper investigates a SAGIN in which low Earth orbit (LEO) satellite constellations communicate with multiple ground hotspots via RIS-assisted UAV relays, serving both FAS-equipped and conventional users.

Abstract

Space-air-ground integrated networks (SAGINs) interconnect satellites, uncrewed aerial vehicles (UAVs), and ground devices to enable flexible and ubiquitous wireless services. The integration of reconfigurable intelligent surfaces (RISs) and fluid antenna systems (FASs) further enhances radio environment controllability. However, the tight integration of cross-layer facilities and radio enhancement technologies leads to pronounced environmental dynamics and heterogeneity, posing fundamental challenges for system modeling and optimization in large-scale SAGINs. This paper investigates a SAGIN in which low Earth orbit (LEO) satellite constellations communicate with multiple ground hotspots via RIS-assisted UAV relays, serving both FAS-equipped and conventional users. A system model is developed that explicitly captures satellite mobility, UAV trajectories, RIS phase control, and heterogeneous user reception capabilities. Accordingly, a multi-hotspot downlink rate maximization problem is studied, whose solvability is analyzed through a hierarchical Stackelberg game. To address heterogeneous and time-varying multi-hotspot environments, an adaptive personalized federated reinforcement learning (FRL) algorithm is proposed for adaptive optimization of UAV trajectories and RIS phase controls. Simulation results demonstrate superior performance and validate the effectiveness of personalization in dynamic heterogeneous SAGIN scenarios.
Paper Structure (20 sections, 2 theorems, 37 equations, 14 figures, 2 tables, 2 algorithms)

This paper contains 20 sections, 2 theorems, 37 equations, 14 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model
  3. Spatial Coordinate Model
  4. Channel Model
  5. Federated Settings
  6. Problem Formulation
  7. Hierarchical Stackelberg Game
  8. Stackelberg Game of UAV Relay and Users
  9. Stackelberg Game of LEO Satellite and UAVs
  10. Markov Game Formulation
  11. Personalized Federated Reinforcement Learning Solution
  12. Local Training
  13. Adaptive Personalization
  14. Global Training
  15. Performance Evaluation
  16. ...and 5 more sections

Key Result

Theorem 1

At each time $t$, the Stackelberg game $\mathcal{G}^{RU}_{n,[t]}$ among UAV-RIS relay $n$ and users $k \in \hat{\mathcal{K}}_{n}[t]$ admits at least one NE.

Figures (14)

  • Figure 1: Hierarchical SAGIN architecture with FRL framework.
  • Figure 2: Illustration of spatial coordinates.
  • Figure 3: Illustration of communication channel.
  • Figure 4: The training workflow of FedPG-AP.
  • Figure 5: Training comparison of 5 runs.
  • ...and 9 more figures

Theorems & Definitions (6)

  • Definition 1: Stackelberg Game $\mathcal{G}^{RU}_{n,[t]}$
  • Definition 2: NE of game $\mathcal{G}^{RU}_{n,[t]}$
  • Theorem 1
  • Definition 3: Stackelberg Game $\mathcal{G}^{LR}_{[t]}$
  • Definition 4: NE of game $\mathcal{G}^{LR}_{[t]}$
  • Theorem 2