Multi-Modal Sensing Data-Based Real-Time Path Loss Prediction for 6G UAV-to-Ground Communications
- 29 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (9) , 2462-2466
Abstract
In this letter, a multi-modal sensing data based real-time path loss prediction scheme for sixth-generation (6G) unmanned aerial vehicle (UAV)-to-ground communications is developed. Meanwhile, a new mixed multi-modal sensing and communication integration dataset in the UAV-to-ground scenario is constructed. Based on the constructed dataset, the mapping relationship between physical space and electromagnetic space is explored, and the multi-modal sensing data based real-time path loss prediction scheme is developed. Simulation results show that the proposed scheme outperforms 3GPP UMa non-line-of-sight (NLoS) and slope-intercept models. By comparing simulation and ray-tracing (RT)-based results, the utility of the proposed scheme is further verified.Keywords
Funding Information
- National Natural Science Foundation of China (62125101, 62341101, 62371273)
- Taishan Scholars Program (tsqn202312307)
- Young Elite Scientists Sponsorship Program by CAST (YESS20230372)
- Natural Science Foundation of Shandong Province (ZR2023YQ058)
- New Cornerstone Science Foundation through the XPLORER PRIZE
This publication has 16 references indexed in Scilit:
- Intelligent Multi-Modal Sensing-Communication Integration: Synesthesia of MachinesIEEE Communications Surveys & Tutorials, 2023
- A UAV-Aided Real-Time Channel Sounder for Highly Dynamic Nonstationary A2G ScenariosIEEE Transactions on Instrumentation and Measurement, 2023
- A Non-Stationary 3D Model for 6G Massive MIMO mmWave UAV ChannelsIEEE Transactions on Wireless Communications, 2021
- UAV-Enabled Ultra-Reliable Low-Latency Communications for 6G: A Comprehensive SurveyIEEE Access, 2021
- A General 3D Space-Time-Frequency Non-Stationary Model for 6G ChannelsIEEE Transactions on Wireless Communications, 2020
- Predicting Path Loss Distribution of an Area From Satellite Images Using Deep LearningIEEE Access, 2020
- Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep LearningIEEE Access, 2019
- Low‐altitude UAV air‐ground propagation channel measurement and analysis in a suburban environment at 3.9 GHzIET Microwaves, Antennas & Propagation, 2019
- AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles2017
- Proposal on Millimeter-Wave Channel Modeling for 5G Cellular SystemIEEE Journal of Selected Topics in Signal Processing, 2016