SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensing
This work addresses the problem of dynamic spectrum sharing for satellite and terrestrial network coexistence, which is crucial for efficient spectrum resource allocation in large-scale deployments.
The paper tackles the challenge of accurate spectrum sensing in space for satellite Internet by proposing a multi-satellite collaborative framework that uses graph neural networks, sub-Nyquist sampling with autoencoder compression, and contrastive learning for packet loss compensation, achieving improved spectrum sensing accuracy compared to conventional deep learning algorithms.
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.