Continuous-Time Channel Prediction Based on Tensor Neural Ordinary Differential Equation

TL;DR

This paper introduces a novel tensor neural ODE-based continuous-time channel prediction method for mobile millimeter wave communications, outperforming existing discrete prediction and interpolation techniques.

Contribution

It develops a TN-ODE scheme that directly predicts intra-frame channels by learning the channel structure, improving accuracy and reducing complexity.

Findings

Achieves higher intra-frame channel prediction accuracy.

Outperforms existing schemes in simulation results.

Effectively captures high-dimensional channel structures.

Abstract

Channel prediction is critical to address the channel aging issue in mobile scenarios. Existing channel prediction techniques are mainly designed for discrete channel prediction, which can only predict the future channel in a fixed time slot per frame, while the other intra-frame channels are usually recovered by interpolation. However, these approaches suffer from a serious interpolation loss, especially for mobile millimeter wave communications. To solve this challenging problem, we propose a tensor neural ordinary differential equation (TN-ODE) based continuous-time channel prediction scheme to realize the direct prediction of intra-frame channels. Specifically, inspired by the recently developed continuous mapping model named neural ODE in the field of machine learning, we first utilize the neural ODE model to predict future continuous-time channels. To improve the channel prediction accuracy and reduce computational complexity, we then propose the TN-ODE scheme to learn the structural characteristics of the high-dimensional channel by low dimensional learnable transform. Simulation results show that the proposed scheme is able to achieve higher intra-frame channel prediction accuracy than existing schemes.