Data-Clustering-Assisted Digital Predistortion for 5G Millimeter-Wave Beamforming Transmitters With Multiple Dynamic Configurations

Motivated by data science, in this article, a data-clustering-assisted digital predistortion (DPD) is proposed to linearize millimeter-wave (mmWave) beamforming transmitters with multiple dynamic configurations. Based on the analysis, similar transmitter states different configurations can be clustered, resulting significant reduction of linearization states. Model complexity within cluster further reduced utilizing penalty factor method. To validate concept, experiments were carried out 16-channel mmWave configurable beam angle, operating frequency, and input power. Total 216 8, 20, 40 unequal optimal model parameters for each state, without losing much performance. The method extended scenario where large scale occur complex structures future wireless systems.