Robust Continuous-Time Beam Tracking with Liquid Neural Network

TL;DR

Problem addressed: reducing beam training overhead and maintaining reliable mmWave links under urban interference. Approach: a robust continuous-time beam tracking framework based on a liquid neural network that ingests pilot measurements, evolves hidden states over a normalized time $\overline{t}$, and outputs a beam index $\hat{q}$ by Softmax over a $Q$-beam codebook $\mathcal{M}$. Key findings: the method yields up to $46.9\%$ higher normalized spectral efficiency $SE_N$ than baselines at UE speed $v=5$ m/s and shows strong robustness to noise and rapid angular variations. Significance: enables real-time, reliable beam alignment for mobile mmWave communications in cluttered urban channels.

Abstract

Millimeter-wave (mmWave) technology is increasingly recognized as a pivotal technology of the sixth-generation communication networks due to the large amounts of available spectrum at high frequencies. However, the huge overhead associated with beam training imposes a significant challenge in mmWave communications, particularly in urban environments with high background noise. To reduce this high overhead, we propose a novel solution for robust continuous-time beam tracking with liquid neural network, which dynamically adjust the narrow mmWave beams to ensure real-time beam alignment with mobile users. Through extensive simulations, we validate the effectiveness of our proposed method and demonstrate its superiority over existing state-of-the-art deep-learning-based approaches. Specifically, our scheme achieves at most 46.9% higher normalized spectral efficiency than the baselines when the user is moving at 5 m/s, demonstrating the potential of liquid neural networks to enhance mmWave mobile communication performance.

Figures (6)

• Figure 1: The beam tracking diagram.
• Figure 2: The LNN cell architecture. Here, $\sigma(\cdot)$ refers to the sigmoid activation function.
• Figure 3: Flowchart of proposed deep learning model based on LNN.
• Figure 4: Performance evaluation with respect to beam training instant.
• Figure 5: Performance evaluation with respect to normalized prediction instant.