A Comprehensive Study of PAPR Reduction Techniques for Deep Joint Source Channel Coding in OFDM Systems

TL;DR

This paper analyzes various PAPR reduction techniques for deep joint source channel coding in OFDM systems, highlighting the effectiveness of deep learning-based methods like clipping with retraining.

Contribution

It provides a comprehensive comparison of conventional and deep learning-based PAPR reduction techniques specifically for DJSCC in OFDM, revealing their relative performance and suitability.

Findings

Clipping with retraining achieves best PAPR reduction and recovery accuracy.

Deep learning-based PAPR techniques outperform conventional methods in DJSCC.

Non-distortion PAPR reduction techniques can reduce PAPR without affecting signal reconstruction.

Abstract

Recently, deep joint source channel coding (DJSCC) techniques have been extensively studied and have shown significant performance with limited bandwidth and low signal to noise ratio. Most DJSCC work considers discrete-time analog transmission, while combining it with orthogonal frequency division multiplexing (OFDM) creates serious high peak-to-average power ratio (PAPR) problem. This paper conducts a comprehensive analysis on the use of various OFDM PAPR reduction techniques in the DJSCC system, including both conventional techniques such as clipping, companding, SLM and PTS, and deep learning-based PAPR reduction techniques such as PAPR loss and clipping with retraining. Our investigation shows that although conventional PAPR reduction techniques can be applied to DJSCC, their performance in DJSCC is different from the conventional split source channel coding. Moreover, we observe that for signal distortion PAPR reduction techniques, clipping with retraining achieves the best performance in terms of both PAPR reduction and recovery accuracy. It is also noticed that signal non-distortion PAPR reduction techniques can successfully reduce the PAPR in DJSCC without compromise to signal reconstruction.