Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kaiqiang Lin, Kangchun Zhao, Yijie Mao

TL;DR

This paper tackles the challenge of reliable downlink communication in satellite-to-underground networks plagued by soil attenuation and air–soil refraction. It introduces a cooperative rate-splitting (CRS) framework with an aboveground relay that decodes and forwards the common stream, and formulates a max-min fairness problem over power allocation, message splitting, and time-slot scheduling. A proximal policy optimization (PPO) based DRL framework with distribution-aware action modeling and a multi-branch actor is developed to solve the non-convex problem under uncertain channels. Across realistic underground pipeline scenarios, the PPO-based CRS significantly outperforms SDMA, RSMA, and greedy CRS benchmarks, demonstrating strong potential for robust, fair, and efficient satellite-to-underground communications.

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.

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

TL;DR

This paper tackles the challenge of reliable downlink communication in satellite-to-underground networks plagued by soil attenuation and air–soil refraction. It introduces a cooperative rate-splitting (CRS) framework with an aboveground relay that decodes and forwards the common stream, and formulates a max-min fairness problem over power allocation, message splitting, and time-slot scheduling. A proximal policy optimization (PPO) based DRL framework with distribution-aware action modeling and a multi-branch actor is developed to solve the non-convex problem under uncertain channels. Across realistic underground pipeline scenarios, the PPO-based CRS significantly outperforms SDMA, RSMA, and greedy CRS benchmarks, demonstrating strong potential for robust, fair, and efficient satellite-to-underground communications.

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 over conventional benchmark strategies across various numbers of UDs and underground conditions.

Paper Structure

This paper contains 5 sections, 14 equations, 3 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. DRL Framework for Resource Allocation
  4. Numerical Results and Discussion
  5. Conclusion

Figures (3)

  • Figure 1: The proposed CRS-aided satellite-to-underground network system with the corresponding time slot allocation for its two transmission phases.
  • Figure 2: Convergence performance of the proposed PPO algorithm for the SDMA, RSMA, and CRS strategies, as well as the greedy-based CRS scheme.
  • Figure 3: Max–min rate performance versus (a) the number of UDs, (b) the burial depth of UDs, and (c) the soil's VWC for the PPO-based SDMA, PPO-based RSMA, greedy-based CRS, and PPO-based CRS strategies, averaged over $512$ random channel realizations.