A Douglas-Rachford Splitting Approach Based Deep Network for MIMO Signal Detection

Signal detection plays a significant role at the receiver of current multiple-input multiple-output (MIMO) communication systems. In this paper, we propose a deep learning aided Douglas-Rachford network (DRNet) for MIMO signal detection. Specifically, DRNet is developed based on Douglas-Rachford splitting approach, which is a classic method for non-smooth convex signal recovery. It is known that the transmitted signal in MIMO systems is drawn from a discrete quadrature amplitude modulation (QAM) constellation and ordinary least square (OLS), namely zero-forcing (ZF), performs poorly in small size MIMO systems. In order to obtain better performance, we design an implicit penalty for the unknown transmitted signal and use a deep neural network (DNN) to learn the corresponding proximal gradient of the penalty. Meanwhile, we vectorize the hyper-parameters in the Douglas-Rachford splitting approach and make them learnable. Simulation results show that the proposed DRNet outperforms the original Douglas-Rachford splitting approach and is robust to varying signal-to-noise ratio (SNR). Moreover, compared with existing model-driven deep MIMO detectors, DRNet also has lower bit-error-rate (BER).