DNN-based Phase Noise Compensation for Sub-THz Communications

Abstract

In this paper, a new method is presented for phase noise (PN) compensation in sub-TeraHertz (THz) orthogonal frequency division multiplexing (OFDM) systems. To suppress the higher PN encountered at the sub-THz spectrum bands, a deep neural network (DNN)-based PN compensation framework is proposed. Exploiting the signal under PN impairment and the channel estimate at the receiver, the proposed DNN framework makes hard decisions with respect to each data subcarrier. Numerical results show the effectiveness of the proposed framework.