Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Attention-Based SINR Estimation in User-Centric Non-Terrestrial Networks

Bruno De Filippo, Alessandro Guidotti, Alessandro Vanelli-Coralli

TL;DR

A low-complexity SINR estimation framework that leverages multi-head self-attention (MHSA) to extract inter-user interference features directly from either channel state information or user location reports is proposed.

Abstract

The signal-to-interference-plus-noise ratio (SINR) is central to performance optimization in user-centric beamforming for satellite-based non-terrestrial networks (NTNs). Its assessment either requires the transmission of dedicated pilots or relies on computing the beamforming matrix through minimum mean squared error (MMSE)-based formulations beforehand, a process that introduces significant computational overhead. In this paper, we propose a low-complexity SINR estimation framework that leverages multi-head self-attention (MHSA) to extract inter-user interference features directly from either channel state information or user location reports. The proposed dual MHSA (DMHSA) models evaluate the SINR of a scheduled user group without requiring explicit MMSE calculations. The architecture achieves a computational complexity reduction by a factor of three in the CSI-based setting and by two orders of magnitude in the location-based configuration, the latter benefiting from the lower dimensionality of user reports. We show that both DMHSA models maintain high estimation accuracy, with the root mean squared error typically below 1 dB with priority-queuing-based scheduled users. These results enable the integration of DMHSA-based estimators into scheduling procedures, allowing the evaluation of multiple candidate user groups and the selection of those offering the highest average SINR and capacity.

Attention-Based SINR Estimation in User-Centric Non-Terrestrial Networks

TL;DR

A low-complexity SINR estimation framework that leverages multi-head self-attention (MHSA) to extract inter-user interference features directly from either channel state information or user location reports is proposed.

Abstract

The signal-to-interference-plus-noise ratio (SINR) is central to performance optimization in user-centric beamforming for satellite-based non-terrestrial networks (NTNs). Its assessment either requires the transmission of dedicated pilots or relies on computing the beamforming matrix through minimum mean squared error (MMSE)-based formulations beforehand, a process that introduces significant computational overhead. In this paper, we propose a low-complexity SINR estimation framework that leverages multi-head self-attention (MHSA) to extract inter-user interference features directly from either channel state information or user location reports. The proposed dual MHSA (DMHSA) models evaluate the SINR of a scheduled user group without requiring explicit MMSE calculations. The architecture achieves a computational complexity reduction by a factor of three in the CSI-based setting and by two orders of magnitude in the location-based configuration, the latter benefiting from the lower dimensionality of user reports. We show that both DMHSA models maintain high estimation accuracy, with the root mean squared error typically below 1 dB with priority-queuing-based scheduled users. These results enable the integration of DMHSA-based estimators into scheduling procedures, allowing the evaluation of multiple candidate user groups and the selection of those offering the highest average SINR and capacity.
Paper Structure (11 sections, 11 equations, 5 figures, 4 tables)

This paper contains 11 sections, 11 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. System model
  3. Dual multi-headed self-attention for SINR estimation
  4. DMHSA Model
  5. Computational complexity
  6. Model training
  7. Results
  8. Random scheduler
  9. PQS scheduler
  10. Conclusions
  11. Acknowledgments

Figures (5)

  • Figure 1: Considered system model.
  • Figure 2: DMHSA SINR estimation model.
  • Figure 3: Computational complexity as a function of $N_C$ with $N_{UE, sched}=24$ (black dashed line corresponds to $N_C=8$).
  • Figure 4: SINR estimation error distribution for different $N_{UE,sched}$ values (random scheduler).
  • Figure 5: CDF of the SINR estimation absolute error with PQS scheduling for different capacity request ranges ($\mathcal{C}_{min}/\mathcal{C}_{max}$).