Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Deep Learning for Path Loss Prediction in the 3.5 GHz CBRS Spectrum Band

Published

Author(s)

Thao T. Nguyen, Raied Caromi, Kassem Kallas

Abstract

In the 3.5 GHz citizen broadband radio service (CBRS) band, accurate path loss prediction is very important to protect the incumbent from harmful interference caused by the lower tier users. Within the current CBRS standards developed by the Wireless Innovation Forum (WInnForum), the irregular terrain model (ITM), also known as the Longley Rice model, is used for path loss calculation. However, the model does not include clutter data, and thus, it underestimates the path loss. This paper utilizes a model-aided deep learning technique with satellite images to improve path loss prediction. Numerical study shows that the proposed approach can outperform the Longley Rice model and some tuned or fitted propagation models.
Proceedings Title
IEEE Wireless Communications and Networking Conference (WCNC)
Conference Dates
April 10-13, 2022
Conference Location
Austin, TX, US
Conference Title
2022 IEEE Wireless Communications and Networking Conference (WCNC)

Keywords

3.5 GHz, CBRS, deep learning, machine learning, path loss prediction

Citation

Nguyen, T. , Caromi, R. and Kallas, K. (2022), Deep Learning for Path Loss Prediction in the 3.5 GHz CBRS Spectrum Band, IEEE Wireless Communications and Networking Conference (WCNC), Austin, TX, US, [online], https://doi.org/10.1109/WCNC51071.2022.9771737, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=933148 (Accessed February 29, 2024)
Created May 19, 2022, Updated November 29, 2022