Path Loss Prediction Modelling for Next-generation Internet-of-Things Applications Using Different Boosting Machine Learning Methods

Wireless channel propagation characteristics are crucial for wireless network systems. The accuracy of the path loss (PL) prediction determines the quality of the received signal and optimization of wireless communication networks.In this paper, we apply and compare various machine learning (ML) boosting methods for the prediction of path loss in cellular communications using a flying base station (FBS). We use a ray tracing technique to obtain the dataset for the training process of the models. The work at hand generates prediction models, based on five different boosting ML learners to accurately predict the path loss of an unmanned aerial vehicle (UAV). The proposed approach exhibits great accuracy and efficiency in predicting the path loss.