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

TL;DR

This paper introduces a low-complexity, attention-based framework for estimating SINR in user-centric non-terrestrial networks, reducing computational load while maintaining high accuracy, thus enhancing scheduling efficiency.

Contribution

It proposes a novel dual multi-head self-attention model that estimates SINR directly from channel or location data, bypassing traditional MMSE calculations and significantly reducing computational complexity.

Findings

Achieves threefold reduction in complexity with CSI data.

Reduces complexity by two orders of magnitude with location data.

Maintains root mean squared error below 1 dB in SINR estimation.

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.