Pairing mobile users using K-means algorithm on PD-NOMA-based mmWaves communications system

Abstract

In this research, we study the effectiveness of the K-means machine learning (ML) clustering approach for pairing mobile users on a power domain nonorthogonal multiple access (PD-NOMA) single input single output (SISO) downlink-based millimeter-wave (mmWave) communication system. The basic concept is to pair the mobile users by using a data set that contains essential information about the mobile users in the micro cell base station (BS) (e.g., the SNR, the distance between the mobile users and the BS, the channel gain, and the data rate of each mobile user). The study conducted in this paper demonstrates that the proposed K-means clustering-based scheme achieves a balance between computational complexity and performance metrics. It outperforms single carrier NOMA (SC-NOMA), the conventional NOMA pairing scheme, and time division multiple access (TDMA), offering an effective trade-off between system efficiency and implementation feasibility.