Deep-Waveform: A Learned OFDM Receiver Based on Deep Complex-valued Convolutional Networks

TL;DR

This paper introduces a deep complex-valued convolutional network that replaces traditional Fourier transforms in OFDM receivers, improving performance and integrating multiple functions like channel estimation and ISI mitigation.

Contribution

It presents a novel learned OFDM receiver architecture using deep complex-valued CNNs that eliminates the need for explicit DFT/IDFT and enhances signal processing capabilities.

Findings

Outperforms traditional channel estimators in Rayleigh fading channels

Effectively exploits cyclic prefix for increased SNR

Demonstrates potential to replace FFT processors with AI accelerators

Abstract

The (inverse) discrete Fourier transform (DFT/IDFT) is often perceived as essential to orthogonal frequency-division multiplexing (OFDM) systems. In this paper, a deep complex-valued convolutional network (DCCN) is developed to recover bits from time-domain OFDM signals without relying on any explicit DFT/IDFT. The DCCN can exploit the cyclic prefix (CP) of OFDM waveform for increased SNR by replacing DFT with a learned linear transform, and has the advantage of combining CP-exploitation, channel estimation, and intersymbol interference (ISI) mitigation, with a complexity of $\mathcal{O}(N^2)$. Numerical tests show that the DCCN receiver can outperform the legacy channel estimators based on ideal and approximate linear minimum mean square error (LMMSE) estimation and a conventional CP-enhanced technique in Rayleigh fading channels with various delay spreads and mobility. The proposed approach benefits from the expressive nature of complex-valued neural networks, which, however, currently lack support from popular deep learning platforms. In response, guidelines of exact and approximate implementations of a complex-valued convolutional layer are provided for the design and analysis of convolutional networks for wireless PHY. Furthermore, a suite of novel training techniques are developed to improve the convergence and generalizability of the trained model in fading channels. This work demonstrates the capability of deep neural networks in processing OFDM waveforms and the results suggest that the FFT processor in OFDM receivers can be replaced by a hardware AI accelerator.