Nonorthogonal multiple access (NOMA) with multi-antenna base station (BS) is a promising technology for next-generation wireless communication, which has high potential in performance and user fairness. Since the performance of NOMA depends on the channel conditions, we can combine NOMA and reconfigurable intelligent surface (RIS), which is a large and passive antenna array and can optimize the wireless channel. However, the high dimensionality makes the RIS optimization a complicated problem. In this work, we propose a machine learning approach to solve the problem of joint optimization of precoding and RIS configuration. We apply the RIS to realize the quasi-degradation of the channel, which allows for optimal precoding in closed form. The neural network architecture RISnet is used, which is designed dedicatedly for RIS optimization. The proposed solution is superior than the works in the literature in terms of performance and computation time.

翻译：非正交多址接入（NOMA）结合多天线基站（BS）是下一代无线通信中一项前景广阔的技术，在性能和用户公平性方面具有巨大潜力。由于NOMA的性能取决于信道条件，我们可以将NOMA与可重构智能表面（RIS）相结合，RIS是一种大规模无源天线阵列，能够优化无线信道。然而，高维度使得RIS优化成为一个复杂问题。本文提出一种机器学习方法来解决预编码与RIS配置的联合优化问题。我们利用RIS实现信道的准退化，从而以闭式形式获得最优预编码。本文采用专门为RIS优化设计的神经网络架构RISnet。所提出的方案在性能和计算时间方面均优于现有文献中的方法。