An end-to-end fiber-based network holds the potential to provide
multi-gigabit fixed access to end-users. However, deploying fiber access,
especially in areas where fiber is non-existent, can be time-consuming and
costly, resulting in delayed returns for Operators. This work investigates
transmission data from fixed broadband wireless access in the mmWave band in
5G. Given the growing interest in this domain, understanding the transmission
characteristics of the data becomes crucial. While existing datasets for the
mmWave band are available, they are often generated from simulated
environments. In this study, we introduce a dataset compiled from real-world
transmission data collected from the Fixed Broadband Wireless Access in mmWave
Band device (RWM6050). The aim is to facilitate self-configuration based on
transmission characteristics. To achieve this, we propose an online machine
learning-based approach for real-time training and classification of
transmission characteristics. Additionally, we present two advanced temporal
models for more accurate classifications. Our results demonstrate the ability
to detect transmission angle and distance directly from the analysis of
transmission data with very high accuracy, reaching up to 99% accuracy on the
combined classification task. Finally, we outline promising future research
directions based on the collected data.

研究了基于纤维的端到端网络在为最终用户提供多千兆位固定接入的潜力，探究了 5G 毫米波段中固定宽带无线接入的传输数据，通过对传输特性的分析，提出了一种在线机器学习的方法来进行实时训练和分类，证明了从传输数据中能够以非常高的准确率直接检测传输角度和距离的能力，并提出了基于收集到的数据的有前景的未来研究方向。