Low PAPR MIMO-OFDM Design Based on Convolutional Autoencoder
share
An enhanced framework for peak-to-average power ratio (𝖯𝖠𝖯𝖱) reduction and waveform design for Multiple-Input-Multiple-Output (𝖬𝖨𝖬𝖮) orthogonal frequency-division multiplexing (𝖮𝖥𝖣𝖬) systems, based on a convolutional-autoencoder (𝖢𝖠𝖤) architecture, is presented. The end-to-end learning-based autoencoder (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) and a multipath fading channel. The offered efficient implementation novel waveform design technique utilizes only a single 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), the 𝖯𝖠𝖯𝖱, and the spectral response and compared with classical 𝖯𝖠𝖯𝖱 reduction 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 reduction, spectrum design, and 𝖬𝖨𝖬𝖮 detection together over a wide range of SNR levels.
READ FULL TEXT
