A 3GPP-Based Height-Dependent LoS Probability Model for A2G Communications

In this paper, combing with the machine learning (ML) principle, a height-dependent line-of-sight (LoS) probability prediction method based on the 3GPP model is developed. We adopt the ray-tracing (RT) simulation method instead of field measurement to acquire channel data and develop the back propagation neural network (BPNN) to estimate height-dependent parameters. In order to introduce the factor of height to the LoS probability, we study the relationship between the parameters and aerial platforms height. The simulation results show that our proposed model can effectively predict the LoS probability for different heights. Moreover, the predicted results match the RT-based ones better than the original method recommended by the 3GPP model.