Abstract: To address the problem that the hybrid precoding scheme based on traditional Particle Swarm Optimization (PSO) algorithm in millimeter Wave (mmWave) massive Multi-Input Multi-Output (MIMO) systems has a low convergence speed and is easy to fall into the local optimal value in the later iteration, a hybrid precoding scheme based on improved PSO algorithm was proposed. Firstly, the particles' position vector and velocity vector were initialized randomly, and the initial swarm optimal position vector was given by maximizing the system sum rate. Secondly, the position vector and velocity vector were updated, and two updated particles' individual-historical-best position vectors were randomly selected to get their weighted sum as the new individual-historical-best position vector, and then some of particles that maximized the system sum rate were picked out. The weighted average value of the individual-historical-best position vectors of these particles was taken as the new swarm optimal position vector and compared with the previous one. After many iterations, the final swarm optimal position vector was formed, which was the desired best hybrid precoding vector. The simulation results show that compared with the hybrid precoding scheme based on traditional PSO algorithm, the proposed scheme is optimized both in terms of convergence speed and sum rate. The convergence speed of the proposed scheme is improved by 100%, and its performance can reach 90% of the full digital precoding scheme. Therefore, the proposed scheme can effectively improve system performance and accelerate convergence.

Key words: millimeter Wave (mmWave), massive Multi-Input Multi-Output (MIMO) technology, hybrid precoding, convergence speed, sum rate

摘要： 针对毫米波大规模多输入多输出（MIMO）系统中基于传统粒子群优化（PSO）算法的混合预编码方案，在迭代后期收敛速度较慢以及容易陷入局部最优值的问题，提出了一种基于改进PSO算法的混合预编码方案。首先，随机初始化粒子的位置矢量和速度矢量，并以最大化系统和速率为目标求解初始群体最优位置矢量；其次，更新位置矢量和速度矢量，并随机地选择更新后的两个粒子的个体历史最优位置矢量进行加权求和作为新的个体历史最优位置矢量，从中挑选出若干个使系统和速率最大的粒子，将其个体历史最优位置矢量的加权平均值作为新的群体最优位置矢量，并与之前的群体最优位置矢量比较，经过多次迭代形成最终的群体最优位置矢量即为所求的最佳混合预编码矢量，并对其进行归一化；最后，根据归一化后的混合预编码矢量设计最终的模拟预编码矩阵和数字预编码矩阵。仿真结果表明，与基于传统PSO算法的混合预编码方案相比，所提改进方案在收敛速度与和速率上都得到优化；其收敛速度提高约100%，且性能可以达到全数字预编码方案的90%，因此，该改进方案能够有效提升系统性能且加快收敛。

关键词: 毫米波, 大规模多输入多输出技术, 混合预编码, 收敛速度, 和速率