Millimeterwave(mmWave, 30–100 GHz) communication is essential for meeting the high data throughput demands of 5G/6G networks. However, mmWave signals are highly susceptible to attenuation and blockage, necessitating directional beamforming antennas and efficient beam tracking algorithms. Traditional machine learning-based approaches, such as centralized learning (CL) and federated learning (FL), face significant challenges. While CL achieves fast convergence, it suffers from high computational costs and privacy concerns. Conversely, FL addresses these issues by enabling distributed model training but struggles with slow convergence and suboptimal accuracy due to data heterogeneity. To overcome these limitations, this paper introduces a novel clustered federated learning (CFL) framework for beam tracking. CFL leverages the benefits of FL while grouping users with similar data distributions, enabling the training of a single model per cluster. This approach reduces communication overhead, accelerates training, and improves accuracy. We analyze key attributes influencing user clustering and their impact on learning efficiency. Numerical results demonstrate that CFL significantly outperforms traditional CL and FL methods, achieving an 18% accuracy improvement over FL (specifically, the FedAvg algorithm) and an 11% enhancement over CL. These findings highlight the potential of CFL for enhancing beam tracking in mmWave systems, offering a more adaptive and privacy-preserving solution for future wireless networks.

Channel state information in millimeter wave (mmWave) and terahertz (THz) communications systems is vital for various tasks ranging from planning the optimal locations of BSs to efficient beam tracking mechanisms to handover design. Due to the use of large-scale phased antenna arrays and high sensitivity to environmental geometry and materials, precise propagation models for these bands are obtained via ray-tracing modeling. However, the propagation conditions in mmWave/THz systems may theoretically change at very small distances, that is, 1 mm–1 $\mathsf{\mu }$m, which requires extreme computational effort for modeling. In this paper, we first will assess the effective correlation distances in mmWave/THz systems for different outdoor scenarios, user mobility patterns, and line-of-sight (LoS) and non-LoS (nLoS) conditions. As the metrics of interest, we utilize the angle of arrival/departure (AoA/AoD) and path loss of the first few strongest rays. Then, to reduce the computational efforts required for the ray-tracing procedure, we propose a methodology for the extrapolation and interpolation of these metrics based on the convolutional long short-term memory (ConvLSTM) model. The proposed methodology is based on a special representation of the channel state information in a form suitable for state-of-the-art video enhancement machine learning (ML) techniques, which allows for the use of their powerful prediction capabilities. To assess the prediction performance of the ConvLSTM model, we utilize precision and recall as the main metrics of interest. Our numerical results demonstrate that the channel state correlation in AoA/AoD parameters is preserved up until approximately 0.3–0.6 m, which is 300–600 times larger than the wavelength at 300 GHz. The use of a ConvLSTM model allows us to accurately predict AoA and AoD angles up to the 0.6 m distance with AoA being characterized by a higher mean squared error (MSE). Our results can be utilized to speed up ray-tracing simulations by selecting the grid step size, resulting in the desired trade-off between modeling accuracy and computational time. Additionally, it can also be utilized to improve beam tracking in mmWave/THz systems via a selection of the time step between beam realignment procedures.