Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Model-based Deep Learning for Wireless Resource Allocation in RSMA Communications Systems

Hanwen Zhang, Mingzhe Chen, Alireza Vahid, Feng Ye, Haijian Sun

TL;DR

This paper proposes a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA by carefully designing the penalty function and embeding a few learnable parameters in each layer of the DU network.

Abstract

Rate-splitting multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond. However, current approaches to RSMA resource management require complicated iterative algorithms, which cannot meet the stringent latency requirement by users with limited resources. Recently, data-driven methods are explored to alleviate this issue. However, they suffer from poor generalizability and scarce training data to achieve satisfactory performance. In this paper, we propose a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA. By carefully designing the penalty function, we couple the variable update with projected gradient descent algorithm (PGD). Following the structure of PGD, we embed a few learnable parameters in each layer of the DU network. Through extensive simulation, we have shown that the proposed model-based neural networks can yield similar results compared to the traditional optimization algorithm for RSMA resource management but with much lower computational complexity, less training data, and higher resilience to out-of-distribution (OOD) data.

Model-based Deep Learning for Wireless Resource Allocation in RSMA Communications Systems

TL;DR

This paper proposes a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA by carefully designing the penalty function and embeding a few learnable parameters in each layer of the DU network.

Abstract

Rate-splitting multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond. However, current approaches to RSMA resource management require complicated iterative algorithms, which cannot meet the stringent latency requirement by users with limited resources. Recently, data-driven methods are explored to alleviate this issue. However, they suffer from poor generalizability and scarce training data to achieve satisfactory performance. In this paper, we propose a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA. By carefully designing the penalty function, we couple the variable update with projected gradient descent algorithm (PGD). Following the structure of PGD, we embed a few learnable parameters in each layer of the DU network. Through extensive simulation, we have shown that the proposed model-based neural networks can yield similar results compared to the traditional optimization algorithm for RSMA resource management but with much lower computational complexity, less training data, and higher resilience to out-of-distribution (OOD) data.
Paper Structure (13 sections, 19 equations, 3 figures, 1 table, 2 algorithms)

This paper contains 13 sections, 19 equations, 3 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model
  3. System Model
  4. Problem Formulation
  5. Proposed Solution
  6. Fractional Programming
  7. Projection Gradient Descent with A Penalty Function
  8. PGD Based Deep Unfolding
  9. Simulation Results
  10. Evaluation Settings and Training Hyper-Parameters
  11. Out-of-distribution Test
  12. Complexity Comparison with FP-based Optimization
  13. Conclusion

Figures (3)

  • Figure 1: Proposed Deep Unfolding Networks Structure Overview
  • Figure 2: Train Set Convergence Performance Comparison with Different Number of Layers
  • Figure 3: Running time CDF of FP and proposed DU