Deep Learning-Based End-to-End Design for OFDM Systems With Hardware Impairments

Abstract

Orthogonal frequency-division multiplexing (OFDM) is a key technology for cellular and Wi-Fi systems, but its performance may be degraded by hardware impairments. Existing works focus mostly on single hardware impairment in OFDM systems, without considering the joint effect of hardware impairments on the entire system. In this paper, hardware impairments including nonlinear power amplification, clipping, in-phase/quadrature-phase (IQ) imbalance, phase noise, carrier frequency offset, and sampling clock offset in OFDM systems are simultaneously considered. We propose end-to-end deep learning-based designs, which jointly optimize transmitter and receiver, to effectively mitigate the performance loss due to hardware impairments. For single-antenna systems and $2\times 2$ multiple-input and multiple-output (MIMO) systems, the proposed design featuring the dense layer neural network (DLNN) significantly outperforms traditional impairment-mitigating methods under both the additive white Gaussian noise (AWGN) channel and the Rayleigh fading channel. Meanwhile, the complexity of the proposed scheme is six times smaller. For $2\times 4$ MIMO systems, the proposed design featuring the residual dense convolution dense neural network (ResNet-DCDNN) outperforms the traditional methods by a large margin. Additionally, transfer learning is applied to effectively address the issue of time-varying impairment levels.

Keywords

• Deep learning
• orthogonal frequency-division multiplexing (OFDM)
• hardware impairments
• end-to-end design
• multiple antennas
• transfer learning