Autoencoder with fitting network for Terahertz wireless communications: A deep learning approach

Terahertz wireless communication has been regarded as an emerging technology to satisfy the ever-increasing demand of ultra-high-speed wireless communications. However, affected by the imperfections of cheap and energy-efficient Terahertz devices, Terahertz signals suffer from serve hybrid distortions, including in-phase/quadrature imbalance, phase noise and nonlinearity, which degrade the demodulation performance significantly. To improve the robustness against these hybrid distortions, an improved autoencoder is proposed, which includes coding the transmitted symbols at the transmitter and decoding the corresponding signals at the receiver. Moreover, due to the lack of information of Terahertz channel during the training of the autoencoder, a fitting network is proposed to approximate the characteristics of Terahertz channel, which provides an approximation of the gradients of loss. Simulation results show that our proposed autoencoder with fitting network can recover the transmitted symbols under serious hybrid distortions, and improves the demodulation performance significantly.