Asymmetric Autoencoder for PAPR Reduction of OFDM Signals

Abstract

Orthogonal frequency division multiplexing (OFDM) signals have a high peak-to-average power ratio (PAPR). Although a method using an autoencoder for PAPR reduction has been proposed, it requires a huge amount of computation for both the transmitter and the receiver. In this paper, we propose a method to reduce the computational complexity of the autoencoder. The proposed method is called an asymmetric autoencoder and is an extension of the conventional method. Numerical experiments show that the proposed method can reduce the computational complexity of the receiver.