User Clustering for Rate Splitting using Machine Learning

TL;DR

This paper proposes a neural network-based user clustering method for hierarchical rate splitting in wireless networks, enabling scalable, efficient clustering based on noisy channel information to improve throughput and interference management.

Contribution

Introduces a lightweight neural network approach for user clustering in HRS schemes, addressing NP-hard complexity with a scalable solution that performs comparably to complex existing methods.

Findings

Neural network effectively clusters users based on noisy CSI.

Achieves rate performance comparable to complex clustering schemes.

Provides a scalable alternative for user clustering in wireless networks.

Abstract

Hierarchical Rate Splitting (HRS) schemes proposed in recent years have shown to provide significant improvements in exploiting spatial diversity in wireless networks and provide high throughput for all users while minimising interference among them. Hence, one of the major challenges for such HRS schemes is the necessity to know the optimal clustering of these users based only on their Channel State Information (CSI). This clustering problem is known to be NP hard and, to deal with the unmanageable complexity of finding an optimal solution, in this work a scalable and much lighter clustering mechanism based on Neural Network (NN) is proposed. The accuracy and performance metrics show that the NN is able to learn and cluster the users based on the noisy channel response and is able to achieve a rate comparable to other more complex clustering schemes from the literature.