Deep Reinforcement Learning-Based Cooperative Rate Splitting for Satellite-to-Underground Communication Networks

2025-10-29

AI Summary

Satellite-to-underground communication suffers from severe signal attenuation in soil and refraction at the air–soil interface, leading to unreliable downlink transmission to underground devices. Method: This paper proposes a cooperative Rate-Splitting Multiple Access (RSMA) framework incorporating a ground-based relay to forward the common message stream, thereby enhancing reception reliability for underground nodes. We formulate a fairness-oriented optimization model jointly optimizing power allocation, message splitting, and time-slot scheduling. To address non-convexity and channel time-variability, we design a distribution-aware action modeling mechanism and a multi-branch actor network within a deep reinforcement learning (DRL) framework. The approach integrates RSMA, relay assistance, and stochastic channel modeling using Proximal Policy Optimization (PPO). Results: Field experiments in real underground pipeline monitoring scenarios demonstrate an average 167% improvement in minimum achievable rate, significantly enhancing multi-user fairness and system robustness.

Technology Category

• Multiagent Systems: Agent Communication
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Reliable downlink communication in satellite-to-underground networks remains challenging due to severe signal attenuation caused by underground soil and refraction in the air-soil interface. To address this, we propose a novel cooperative rate-splitting (CRS)-aided transmission framework, where an aboveground relay decodes and forwards the common stream to underground devices (UDs). Based on this framework, we formulate a max-min fairness optimization problem that jointly optimizes power allocation, message splitting, and time slot scheduling to maximize the minimum achievable rate across UDs. To solve this high-dimensional non-convex problem under uncertain channels, we develop a deep reinforcement learning solution framework based on the proximal policy optimization (PPO) algorithm that integrates distribution-aware action modeling and a multi-branch actor network. Simulation results under a realistic underground pipeline monitoring scenario demonstrate that the proposed approach achieves average max-min rate gains exceeding $167%$ over conventional benchmark strategies across various numbers of UDs and underground conditions.

Problem

• Addressing severe signal attenuation in satellite-to-underground communication networks
• Optimizing power allocation and scheduling for max-min fairness across devices
• Solving high-dimensional non-convex optimization under uncertain channel conditions

Innovation

• Cooperative rate-splitting framework with aboveground relay
• Deep reinforcement learning optimizes power and scheduling
• Proximal policy algorithm handles uncertain underground channels