Spectrum Efficiency Optimization of Hybrid Precoding Based on Adam-PGD Algorithm

Train-to-Ground (T2G) is widely used in wireless communication of high-speed railway. Aiming at the problems of various infrastructures, weak anti-interference ability and limited system capacity in traditional methods, a transmission scheme of Hybrid Precoding (HP) for Train-to-Train (T2T) communication is proposed. A fully connected multi-layer perceptron is designed by combining the key technologies of the fifth generation mobile communication (5G) system <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[1]</sup>, such as millimeter wave (mmWave), massive multiple input multiple output (MIMO) and HP. At the same time, the Adaptive Moment Estimation (Adam) algorithm and the Projected Gradient Descent (PGD) algorithm are introduced to optimize the HP scheme. The simulation results show that the proposed HP is close to the performance of the optimal all-digital precoder and much better than the analog precoder. By analyzing the influence of the number of radio frequency (RF) links and T2T communication distance on the spectrum efficiency of the system, the proposed scheme is obtained through detailed comparison, which can provide theoretical guidance for the design of T2T communication of high-speed railway in the future.