Channel Estimation for MIMO-OTFS Satellite Communication: a Deep Learning-Based Approach

The orthogonal time frequency space (OTFS) modulation has garnered significant attention due to its potential to combat the frequency Doppler effect in high-mobility scenarios, especially in the low earth orbit (LEO) satellite communication. However, facilitating the OTFS in multiple-input and multipleoutput (MIMO) satellite communication requires accurate channel state information, which is a challenging task. To this end, we propose a novel deep-learning-based framework to enhance the channel estimation accuracy in a MIMO satellite communication network by exploiting the channel correlation of the OTFS-MIMO channels. Through extensive simulations, our proposed framework shows an impressive capability to predict MIMO-OTFS channels with remarkable accuracy enhancement. The effect of dataset and data distribution on the channel estimation accuracy and generalization are also revealed.

I. Introduction

The concept of the space-terrestrial integrated network (STIN) holds great promise in realizing the 6G vision of achieving ubiquitous global coverage. Satellites, especially the LEO satellites, can flexibly and cost-effectively provide high throughput for areas without terrestrial network coverage [1]. However, satellite communications using orthogonal frequency-division multiplexing (OFDM) suffers from the severe Doppler frequency shift brought by the ultra-high velocity of LEOs [2]. To resolve this challenge, OTFS has emerged as a promising waveform by transforming the time-frequency domain signal into the delay-Doppler domain to combat the severe doppler frequency shift in the LEO communication networks [3].