DỰ ĐOÁN SUY HAO ĐƯỜNG TRUYỀN KHÔNG TRUNG - MẶT ĐẤT ĐA TẦN SỐ CHO UAV SỬ DỤNG HỌC MÁY

Abstract

Unmanned Aerial Vehicles (UAVs) have emerged as a promising solution for modern wireless communication systems due to their flexibility, mobility, and ease of deployment. However, ensuring reliable air-to-ground (A2G) communication requires accurate channel modeling to support efficient power control and system planning. This study proposes a robust path loss prediction framework for A2G communication links using machine learning techniques, specifically the K-Nearest Neighbors (KNN) regression algorithm. The model is trained and evaluated using a publicly available dataset, with a focus on urban environments and tested across three carrier frequencies: 1 GHz, 2 GHz, and 5.8 GHz. Comparative evaluations against conventional A2G models demonstrate that the proposed approach achieves lower standard errors and narrower confidence intervals. These results highlight the model’s capability to deliver accurate path loss predictions, underscoring its potential for improving the reliability and performance of UAV-based communication systems, particularly in dense urban scenarios