Low-complexity signal detection networks based on Gauss-Seidel iterative method for massive MIMO systems

Abstract

The traditional Gauss-Seidel iterative method runs in parallel with high complexity. To reduce the complexity, this paper proposes a model-driven Deep learning(DL) detector network, namely Block Gauss-Seidel Network(BGS-Net), which is based on the Gauss-Seidel iterative method. We reduce complexity by converting a large matrix inversion to small matrix inversions. Single-antenna user equipment (SAUE) and multiple-antenna user equipment (MAUE) systems under Rayleigh channel are considered in this paper. In order to improve the Symbol Error Ratio(SER) of BGS-Net under MAUE system, we improve the accuracy of the initial solution of BGS-Net, called Improved BGS-Net. The simulation results show that, compared with the existing model-driven algorithms, BGS-Net has lower complexity and similar SER; good robustness, and its performance is less affected by changes in the number of antennas; SER is better than traditional Gauss-Seidel; Improved BGS-Net can improve the SER of BGS-Net.