Spiking Neural Networks for Detecting Satellite-Based Internet-of-Things Signals

TL;DR

This work tackles the challenge of detecting uplink IoT signals in interference-heavy LEO satellite links with stringent power constraints. It proposes spiking neural networks (SNNs) and convolutional SNNs (CSNNs), including a HybNet hybrid architecture that can switch between spiking detectors and a non-coherent matched filter to optimize performance and energy use. Using a LoRa chirp-based modulation in a Walker-Delta LEO constellation and a mixed LoS/nLoS channel with Doppler, the study demonstrates that DL and spiking detectors outperform traditional non-coherent detection under interference, while SNNs offer significant energy savings, particularly on neuromorphic hardware. The results support onboard deployment of energy-efficient SNN-based receivers for IoT-over-satellite systems and highlight HybNet as a practical pathway to balance detection accuracy and power consumption in dynamic interference environments.

Abstract

With the rapid growth of IoT networks, ubiquitous coverage is becoming increasingly necessary. Low Earth Orbit (LEO) satellite constellations for IoT have been proposed to provide coverage to regions where terrestrial systems cannot. However, LEO constellations for uplink communications are severely limited by the high density of user devices, which causes a high level of co-channel interference. This research presents a novel framework that utilizes spiking neural networks (SNNs) to detect IoT signals in the presence of uplink interference. The key advantage of SNNs is the extremely low power consumption relative to traditional deep learning (DL) networks. The performance of the spiking-based neural network detectors is compared against state-of-the-art DL networks and the conventional matched filter detector. Results indicate that both DL and SNN-based receivers surpass the matched filter detector in interference-heavy scenarios, owing to their capacity to effectively distinguish target signals amidst co-channel interference. Moreover, our work highlights the ultra-low power consumption of SNNs compared to other DL methods for signal detection. The strong detection performance and low power consumption of SNNs make them particularly suitable for onboard signal detection in IoT LEO satellites, especially in high interference conditions.

Figures (11)

• Figure 1: An illustration of the leaky integrate-and-fire neuron model.
• Figure 2: Walker-Delta orbit simulation using 384 satellites with an orbital inclination of $53^\circ$.
• Figure 3: LEO satellite scenario showing the concept of Earth-centered zenith angle $\varphi$ and the satellite beamwidth $\psi$.
• Figure 4: A simulation snapshot showing the distribution of user devices and the satellite footprint. The red line from the ground user to the satellite indicates that even though the user is not being served by the satellite with the link, it still contributes to the interference.
• Figure 5: An illustration of the pure-ALOHA access model used for IoT-over-Satellite.