Air-to-Air Path Loss Prediction Based on Machine Learning Methods in Urban Environments

Abstract

Recently, unmanned aerial vehicle (UAV) plays an important role in many applications because of its high flexibility and low cost. To realize reliable UAV communications, a fundamental work is to investigate the propagation characteristics of the channels. In this paper, we propose path loss models for the UAV air-to-air (AA) scenario based on machine learning. A ray-tracing software is employed to generate samples for multiple routes in a typical urban environment, and different altitudes of Tx and Rx UAVs are taken into consideration. Two machine-learning algorithms, Random Forest and KNN, are exploited to build prediction models on the basis of the training data. The prediction performance of trained models is assessed on the test set according to the metrics including the mean absolute error (MAE) and root mean square error (RMSE). Meanwhile, two empirical models are presented for comparison. It is shown that the machine-learning-based models are able to provide high prediction accuracy and acceptable computational efficiency in the AA scenario. Moreover, Random Forest outperforms other models and has the smallest prediction errors. Further investigation is made to evaluate the impacts of five different parameters on the path loss. It is demonstrated that the path visibility is crucial for the path loss.

A Two-Step Environment-Learning-Based Method for Optimal UAV Deployment

“…For regression or prediction problems, the output of the random forest is the average of the outputs of all the decision trees. We have demonstrated in previous works [29]- [31] that the random forest has high accuracy in the estimation of channel qualities.…”

A Survey on Machine-Learning Techniques for UAV-Based Communications

“…Aiming to study the application of ML on PL prediction for the air-to-air channels, the authors of Reference [41] proposed various ML-based PL models for urban environments. The considered ML algorithms consisted of the random forest (RandF) and KNN.…”

FadeNet: Deep Learning-Based mm-Wave Large-Scale Channel Fading Prediction and its Applications

“…In [28], an MLP is designed to predict the point-to-point LSF using the TX-RX distance, TX/RX heights, diffraction loss for the line-ofsight (LoS) path and crossed distance in each clutter type as inputs. In [29], the LSF for the air-to-air channel between unmanned aerial vehicles was predicted using TX/RX altitude, distance, LoS feature and elevation angle as inputs. In [30], the authors use deep convolutional neural networks to predict the point-to-point LSF using some environmental features surrounding the RX.…”