SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensing

TL;DR

SATSense introduces a collaborative multi-satellite framework utilizing graph neural networks, data compression, and contrastive learning to enhance spectrum sensing accuracy in space, addressing challenges of heterogeneity and data loss.

Contribution

The paper presents a novel multi-satellite collaborative spectrum sensing scheme combining graph neural networks, sub-Nyquist sampling, autoencoder compression, and contrastive learning.

Findings

Achieves higher spectrum sensing accuracy than traditional deep learning methods.

Effectively reduces data transmission via joint sampling and autoencoder compression.

Successfully compensates for missing data packets using contrastive learning.

Abstract

Low Earth Orbit satellite Internet has recently been deployed, providing worldwide service with non-terrestrial networks. With the large-scale deployment of both non-terrestrial and terrestrial networks, limited spectrum resources will not be allocated enough. Consequently, dynamic spectrum sharing is crucial for their coexistence in the same spectrum, where accurate spectrum sensing is essential. However, spectrum sensing in space is more challenging than in terrestrial networks due to variable channel conditions, making single-satellite sensing unstable. Therefore, we first attempt to design a collaborative sensing scheme utilizing diverse data from multiple satellites. However, it is non-trivial to achieve this collaboration due to heterogeneous channel quality, considerable raw sampling data, and packet loss. To address the above challenges, we first establish connections between the satellites by modeling their sensing data as a graph and devising a graph neural network-based algorithm to achieve effective spectrum sensing. Meanwhile, we establish a joint sub-Nyquist sampling and autoencoder data compression framework to reduce the amount of transmitted sensing data. Finally, we propose a contrastive learning-based mechanism compensates for missing packets. Extensive experiments demonstrate that our proposed strategy can achieve efficient spectrum sensing performance and outperform the conventional deep learning algorithm in spectrum sensing accuracy.