Low-Complexity Precoding for Millimeter Wave MIMO Systems with Finite Alphabet Inputs

This paper considers low-complexity hybrid analog-digital precoding for millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with finite alphabet inputs. We analyze the mutual information with finite alphabet inputs in the extreme signal-to-noise ratio (SNR) region. At low SNR, we find out that it is optimal to transmit signals through its strongest sub-channel, and thus formulate the analog precoding problem as a single-variable optimization problem. An iterative coordinate descent algorithm is developed to obtain the near-optimal hybrid precoder. At high SNR, the mutual information degrades when the Gaussian scheme is directly applied into the practical systems with finite alphabet inputs. Therefore, a modified fully-digital precoder is proposed to improve the mutual information. Numerical results validate that the proposed schemes achieve a good trade-off between mutual information and computational complexity.