Random Access for LEO Satellite Communication Systems via Deep Learning

TL;DR

LEO SatComs impose long RTTs, large Doppler shifts, and high concurrent access, challenging conventional random access. The authors develop a deep-learning–driven framework that detects preamble collisions early using antenna-wise correlation inputs fed into a lightweight 1D CNN and applies an opportunistic Step 3 transmission policy to balance access probability with resource use. Under 3GPP-compliant LEO settings, the approach improves access success probability, reduces delay, and increases PUSCH utilization while lowering computational burden versus prior schemes. The work provides a practical path to adapt terrestrial RA concepts to LEO environments by leveraging early collision information and probabilistic contention resolution, with implications for satellite IoT and direct-to-device services.

Abstract

Integrating contention-based random access procedures into low Earth orbit (LEO) satellite communication (SatCom) systems poses new challenges, including long propagation delays, large Doppler shifts, and a large number of simultaneous access attempts. These factors degrade the efficiency and responsiveness of conventional random access schemes, particularly in scenarios such as satellite-based internet of things and direct-to-device services. In this paper, we propose a deep learning-based random access framework designed for LEO SatCom systems. The framework incorporates an early preamble collision classifier that uses multi-antenna correlation features and a lightweight 1D convolutional neural network to estimate the number of collided users at the earliest stage. Based on this estimate, we introduce an opportunistic transmission scheme that balances access probability and resource efficiency to improve success rates and reduce delay. Simulation results under 3GPP-compliant LEO settings confirm that the proposed framework achieves higher access success probability, lower delay, better physical uplink shared channel utilization, and reduced computational complexity compared to existing schemes.

Figures (8)

• Figure 1: Conventional contention-based random access procedure for LEO SatCom systems.
• Figure 2: Preamble detection process in the SBS. The SBS computes the correlation values for each predefined ZCZ and then detects the presence of preambles based on a threshold.
• Figure 3: Proposed random access framework for LEO SatCom systems. The framework modifies the conventional random access procedure by incorporating an early preamble collision classifier and an opportunistic transmission scheme for Step 3.
• Figure 4: Structure of the proposed early preamble collision classifier. The classifier uses antenna-wise correlation values as input and consists of two 1D convolutional layers followed by a fully connected layer.
• Figure 5: Misdetection and false alarm probabilities of the proposed preamble collision classifier, with models trained individually at each SNR.