SmartUT: Receive Beamforming for Spectral Coexistence of NGSO Satellite Systems

2025-05-12

AI Summary

To address co-frequency interference (CFI) suppression in the downlink of non-geostationary orbit (NGSO) satellite systems, conventional adaptive beamforming methods—such as zero-forcing (ZF) and sample matrix inversion (SMI)—suffer from high computational complexity, reliance on accurate channel state information (CSI), and severe performance degradation under limited snapshot availability. This paper introduces Mamba, a state-space sequence model, into unsupervised edge-side beamforming for the first time. The proposed method operates without CSI and requires only a minimal number of array snapshots. By synergistically integrating unsupervised deep learning with array signal processing—and avoiding explicit matrix inversion—it achieves robust interference suppression and significantly improves signal-to-interference-plus-noise ratio (SINR). Extensive evaluation demonstrates consistent superiority over ZF and SMI across challenging scenarios, including low SINR, snapshot scarcity, and CSI mismatch.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In this paper, we investigate downlink co-frequency interference (CFI) mitigation in non-geostationary satellites orbits (NGSOs) co-existing systems. Traditional mitigation techniques, such as Zero-forcing (ZF), produce a null towards the direction of arrivals (DOAs) of the interfering signals, but they suffer from high computational complexity due to matrix inversions and required knowledge of the channel state information (CSI). Furthermore, adaptive beamformers, such as sample matrix inversion (SMI)-based minimum variance, provide poor performance when the available snapshots are limited. We propose a Mamba-based beamformer (MambaBF) that leverages an unsupervised deep learning (DL) approach and can be deployed on the user terminal (UT) antenna array, for assisting downlink beamforming and CFI mitigation using only a limited number of available array snapshots as input, and without CSI knowledge. Simulation results demonstrate that MambaBF consistently outperforms conventional beamforming techniques in mitigating interference and maximizing the signal-to-interference-plus-noise ratio (SINR), particularly under challenging conditions characterized by low SINR, limited snapshots, and imperfect CSI.

Problem

• Mitigate downlink co-frequency interference in NGSO satellite systems
• Reduce computational complexity without needing channel state information
• Improve beamforming performance with limited snapshots and low SINR

Innovation

• MambaBF uses unsupervised deep learning for beamforming
• Works without CSI knowledge and limited snapshots
• Outperforms traditional methods in low SINR conditions