Autoencoder-Based End-to-End OTFS System Design With Hardware Impairments

Abstract

Orthogonal time-frequency space (OTFS) modulation is an innovative waveform which effectively multiplexes information symbols across a delay-Doppler (DD) plane, resulting in a superior performance, particularly in doubly dispersive channels. At higher carrier frequencies, the hardware impairments (HIs) at transceivers significantly degrade the performance of OTFS wireless systems. To mitigate the impact of HIs, conventionally an HI-aware channel equalization is performed, which is difficult to achieve in practice. In contrast to this, an autoencoder-based end-to-end design for OTFS (AE-OTFS) system is proposed, which does not require HI-aware channel equalization. Due to its end-to-end design approach, the proposed AE-OTFS significantly enhances the error performance of the OTFS system in the presence of HIs. In particular, it is found that the proposed HI-aware AE-OTFS achieves approximately 3 dB higher performance compared to existing autoencoder based OTFS design, which does not consider the impact of HIs. In addition, comparisons are performed against the conventional OTFS system with state-of-the-art signal detectors for HI-compensation, based on convolutional neural network (CNN), and it is found that due to its end-to-end design the proposed AE-OTFS results in signal-to-noise ratio improvement of up to 8 dB. © 2012 IEEE.