20
6

Low PAPR MIMO-OFDM Design Based on Convolutional Autoencoder

Abstract

An enhanced framework for peak-to-average power ratio (PAPR\mathsf{PAPR}) reduction and waveform design for Multiple-Input-Multiple-Output (MIMO\mathsf{MIMO}) orthogonal frequency-division multiplexing (OFDM\mathsf{OFDM}) systems, based on a convolutional-autoencoder (CAE\mathsf{CAE}) architecture, is presented. The end-to-end learning-based autoencoder (AE\mathsf{AE}) for communication networks represents the network by an encoder and decoder, where in between, the learned latent representation goes through a physical communication channel. We introduce a joint learning scheme based on projected gradient descent iteration to optimize the spectral mask behavior and MIMO detection under the influence of a non-linear high power amplifier (HPA\mathsf{HPA}) and a multipath fading channel. The offered efficient implementation novel waveform design technique utilizes only a single PAPR\mathsf{PAPR} reduction block for all antennas. It is throughput-lossless, as no side information is required at the decoder. Performance is analyzed by examining the bit error rate (BER\mathsf{BER}), the PAPR\mathsf{PAPR}, and the spectral response and compared with classical PAPR\mathsf{PAPR} reduction MIMO\mathsf{MIMO} detector methods on 5G simulated data. The suggested system exhibits competitive performance when considering all optimization criteria simultaneously. We apply gradual loss learning for multi-objective optimization and show empirically that a single trained model covers the tasks of PAPR\mathsf{PAPR} reduction, spectrum design, and MIMO\mathsf{MIMO} detection together over a wide range of SNR levels.

View on arXiv
Comments on this paper