A geometric multiple-input multiple-output (MIMO) channel model is proposed for millimeter-wave (mmWave) mobile-to-mobile (M2M) applications based on the two-ring reference model, where the cluster-based nonisotropic scattering at both ends of the radio link is considered. The proposed model employs a few clusters of scatterers located on the two rings centered on the transmitter and receiver, and intra-cluster azimuth spread of scatterers is further characterized according to mmWave channel characteristics. From the model, the time-frequency correlation function, power delay profile (PDP), and Doppler power spectrum are derived. By adjusting cluster number, cluster center position, and degree of intra-cluster nonisotropic scattering, the model is adaptable to a variety of M2M scenarios. Model validation is further conducted by comparing the simulated PDPs with mmWave outdoor measurements. Based on the detailed investigation of channel correlation functions, it is found that a small number of clusters lead to high channel correlation, and the degree of intra-cluster nonisotropic scattering has major impact on correlation only if cluster number is small. In addition, the Doppler power spectrum is similar to the U-shaped spectrum, and several factors (e.g., small cluster number, high intra-cluster azimuth spread, and large antenna spacing) introduce significant fluctuations in the spectrum. Finally, the model is implemented with directional antennas for safety related M2M scenarios, which leads to high channel correlation compared with using omnidirectional antennas. These observations and conclusions can be considered as a guidance for mmWave M2M MIMO system design.

This two-part paper investigates the application of artificial intelligence (AI) and, in particular, machine learning (ML) to the study of wireless propagation channels. In Part I of this article, we introduced AI and ML and provided a comprehensive survey on ML-enabled channel characterization and antenna-channel optimization, and in this part (Part II), we review the state-of-the-art literature on scenario identification and channel modeling here. In particular, the key ideas of ML for scenario identification and channel modeling/prediction are presented, and the widely used ML methods for propagation scenario identification and channel modeling and prediction are analyzed and compared. Based on the state of the art, the future challenges of AI-/ML-based channel data processing techniques are given as well.

Cluster-based channel modeling has been an important trend in the development of channel model, as it maintains accuracy while reducing complexity. Whereas a large number of channel measurements have shown that multipath components (MPCs) are distributed as groups, i.e., clusters, existing clustering algorithms have various drawbacks with respect to complexity, threshold choices, and/or assumptions about prior knowledge. In this paper, a kernel-power-density (KPD)-based algorithm is proposed for MPC clustering. It uses the kernel density of MPCs to incorporate the modeled behavior of MPCs and takes into account the power of the MPCs. Furthermore, the KPD algorithm only considers the K nearest MPCs in the density estimation to better identify the local density variations of MPCs. A heuristic approach of cluster merging is used to improve the performance. Both simulation and channel measurements validate the KPD algorithm, and almost no performance degradation is found even with a large number of clusters and large cluster angular spread, which outperforming other algorithms. The KPD algorithm enables applications in multipleinput-multiple-output channels with no prior knowledge about the clusters, such as number and initial locations. It also has a fairly low computational complexity and can be used for clusterbased channel modeling.