Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Deep Learning Approach for User-Centric Clustering in Cell-Free Massive MIMO Systems

Giovanni Di Gennaro, Amedeo Buonanno, Gianmarco Romano, Stefano Buzzi, Francesco A. N Palmieri

TL;DR

A solution based on deep learning is proposed to solve the user clustering problem aimed at maximizing the sum spectral efficiency while controlling the number of active connections, and can scale effectively with the number of users.

Abstract

Contrary to conventional massive MIMO cellular configurations plagued by inter-cell interference, cell-free massive MIMO systems distribute network resources across the coverage area, enabling users to connect with multiple access points (APs) and boosting both system capacity and fairness across user. In such systems, one critical functionality is the association between APs and users: determining the optimal association is indeed a combinatorial problem of prohibitive complexity. In this paper, a solution based on deep learning is thus proposed to solve the user clustering problem aimed at maximizing the sum spectral efficiency while controlling the number of active connections. The proposed solution can scale effectively with the number of users, leveraging long short-term memory cells to operate without the need for retraining. Numerical results show the effectiveness of the proposed solution, even in the presence of imperfect channel state information due to pilot contamination.

A Deep Learning Approach for User-Centric Clustering in Cell-Free Massive MIMO Systems

TL;DR

A solution based on deep learning is proposed to solve the user clustering problem aimed at maximizing the sum spectral efficiency while controlling the number of active connections, and can scale effectively with the number of users.

Abstract

Contrary to conventional massive MIMO cellular configurations plagued by inter-cell interference, cell-free massive MIMO systems distribute network resources across the coverage area, enabling users to connect with multiple access points (APs) and boosting both system capacity and fairness across user. In such systems, one critical functionality is the association between APs and users: determining the optimal association is indeed a combinatorial problem of prohibitive complexity. In this paper, a solution based on deep learning is thus proposed to solve the user clustering problem aimed at maximizing the sum spectral efficiency while controlling the number of active connections. The proposed solution can scale effectively with the number of users, leveraging long short-term memory cells to operate without the need for retraining. Numerical results show the effectiveness of the proposed solution, even in the presence of imperfect channel state information due to pilot contamination.
Paper Structure (8 sections, 15 equations, 5 figures, 2 tables)

This paper contains 8 sections, 15 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System model
  3. Communication process
  4. Channel estimation
  5. Downlink operation
  6. Problem formulation and DL approach
  7. Simulation results
  8. Conclusions

Figures (5)

  • Figure 1: Deep learning framework using UE ordering by master APs.
  • Figure 2: Example of AP positions within the area, with random variability on both axes compared to the points of an underlying imaginary grid.
  • Figure 3: Statistics for both scenarios relating: (a) the distribution of the sum of SE values compared to the approach outlined in Bjornson2020, and (b) the distribution of the number of connections activated by our approach.
  • Figure 4: Example illustrating connections between UEs and APs with $\tau_p=3$: (a) as per the approach outlined in Bjornson2020, and (b) our approach after training.
  • Figure 5: Example illustrating connections between UEs and APs with $\tau_p=10$: (a) as per the approach outlined in Bjornson2020, and (b) our approach after training.