K-medoids and BIRCH Clustering Methods for Analyzing 6G High MmWave Bands

Since the early stages of advanced mobile phone systems (AMPS), in the first generation (1G), mobile systems have significantly evolved. Today, with 5G and beyond, big data and artificial intelligence (AI) have created a new era in communication systems. This has led to the research and development of 6G wireless communication, which will become available in the early 2030s. 6G wireless communications will overcome the drawbacks of previous generations using high mmWave and terahertz (THz) frequencies combined with AI. This chapter presents an analysis of clustering models for binary variable analysis. The objective is to evaluate the performance of these models and gain insights into the underlying data patterns of the 145 GHz frequency in an urban microenvironment. The selected 145 GHz band falls within the millimeter wave (mmWave) band, which offers an extremely high bandwidth compared to those at lower frequencies. This enables the transmission of large amounts of data, making it effective for applications such as highspeed data links and future generations of wireless communication (e.g., 6G). Moreover, this frequency has not been investigated because the signal attenuation (weakening) is greater at these frequencies, limiting the transmission range. K-medoids and BIRCH clustering techniques are used to understand the relationship between channel state information (CSI). Using metrics and visualizations, the author aims to provide a comprehensive understanding of the data and facilitate informed decision-making. K-medoids and BIRCH clustering techniques have been used to understand the relationship between CSI.