Predictive Precoder Design for OTFS-Enabled URLLC: A Deep Learning Approach

TL;DR

This paper introduces a deep learning-based predictive precoder design for OTFS-enabled URLLC that predicts precoders using historical channel data, reducing reliance on perfect channel information and improving reliability.

Contribution

It proposes a novel DL framework utilizing an unsupervised CLSTM network for precoder prediction based on delay-Doppler channels, enhancing reliability without requiring instantaneous channel info.

Findings

Achieves near-optimal FER performance approaching genie-aided bounds.

Provides a flexible reliability-latency tradeoff in URLLC systems.

Demonstrates the effectiveness of DL-based precoding in OTFS for URLLC.

Abstract

This paper investigates the orthogonal time frequency space (OTFS) transmission for enabling ultra-reliable low-latency communications (URLLC). To guarantee excellent reliability performance, pragmatic precoder design is an effective and indispensable solution. However, the design requires accurate instantaneous channel state information at the transmitter (ICSIT) which is not always available in practice. Motivated by this, we adopt a deep learning (DL) approach to exploit implicit features from estimated historical delay-Doppler domain channels (DDCs) to directly predict the precoder to be adopted in the next time frame for minimizing the frame error rate (FER), that can further improve the system reliability without the acquisition of ICSIT. To this end, we first establish a predictive transmission protocol and formulate a general problem for the precoder design where a closed-form theoretical FER expression is derived serving as the objective function to characterize the system reliability. Then, we propose a DL-based predictive precoder design framework which exploits an unsupervised learning mechanism to improve the practicability of the proposed scheme. As a realization of the proposed framework, we design a DDCs-aware convolutional long short-term memory (CLSTM) network for the precoder design, where both the convolutional neural network and LSTM modules are adopted to facilitate the spatial-temporal feature extraction from the estimated historical DDCs to further enhance the precoder performance. Simulation results demonstrate that the proposed scheme facilitates a flexible reliability-latency tradeoff and achieves an excellent FER performance that approaches the lower bound obtained by a genie-aided benchmark requiring perfect ICSI at both the transmitter and receiver.