LLM-guided DRL for Multi-tier LEO Satellite Networks with Hybrid FSO/RF Links

2025-05-17

AI Summary

To address coverage gaps, frequent handovers, and challenges in joint optimization of free-space optical (FSO) and radio-frequency (RF) links in multi-layer aerial–space networks comprising low-Earth-orbit (LEO) satellites and high-altitude platforms (HAPs), this paper proposes the LLM-Guided Truncated Quantile Critic algorithm with Dynamic Action Masking (LTQC-DAM). LTQC-DAM innovatively integrates a large language model (LLM) to enable autonomous hyperparameter tuning and dynamic action masking—thereby suppressing ineffective exploration—and jointly models hybrid FSO/RF resource allocation under multi-timescale constraints. Experiments demonstrate that LTQC-DAM achieves significantly faster convergence than baseline deep reinforcement learning (DRL) methods, improves downlink throughput by 23.6%, and reduces manual handover frequency by 41.2%. This work validates the efficacy of LLM-augmented DRL for joint optimization in highly dynamic aerial–space networks and provides a scalable solution for remote-area and post-disaster emergency communications.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Despite significant advancements in terrestrial networks, inherent limitations persist in providing reliable coverage to remote areas and maintaining resilience during natural disasters. Multi-tier networks with low Earth orbit (LEO) satellites and high-altitude platforms (HAPs) offer promising solutions, but face challenges from high mobility and dynamic channel conditions that cause unstable connections and frequent handovers. In this paper, we design a three-tier network architecture that integrates LEO satellites, HAPs, and ground terminals with hybrid free-space optical (FSO) and radio frequency (RF) links to maximize coverage while maintaining connectivity reliability. This hybrid approach leverages the high bandwidth of FSO for satellite-to-HAP links and the weather resilience of RF for HAP-to-ground links. We formulate a joint optimization problem to simultaneously balance downlink transmission rate and handover frequency by optimizing network configuration and satellite handover decisions. The problem is highly dynamic and non-convex with time-coupled constraints. To address these challenges, we propose a novel large language model (LLM)-guided truncated quantile critics algorithm with dynamic action masking (LTQC-DAM) that utilizes dynamic action masking to eliminate unnecessary exploration and employs LLMs to adaptively tune hyperparameters. Simulation results demonstrate that the proposed LTQC-DAM algorithm outperforms baseline algorithms in terms of convergence, downlink transmission rate, and handover frequency. We also reveal that compared to other state-of-the-art LLMs, DeepSeek delivers the best performance through gradual, contextually-aware parameter adjustments.

Problem

• Optimizing downlink rate and handover frequency in LEO satellite networks
• Addressing high mobility and dynamic channel conditions in hybrid FSO/RF links
• Enhancing connectivity reliability in multi-tier satellite-ground networks

Innovation

• Hybrid FSO/RF links for reliable connectivity
• LLM-guided DRL optimizes network performance
• Dynamic action masking reduces exploration overhead