Radio Environment

Understanding and predicting radio environments is crucial for optimizing wireless communication systems, particularly in demanding applications like autonomous driving and 6G networks. Current research focuses on developing accurate spatial prediction models, often employing deep learning techniques like convolutional neural networks and tree-ensemble methods, and integrating these models with advanced technologies such as ray tracing and reconfigurable intelligent surfaces to improve prediction accuracy and robustness. These advancements aim to enhance the reliability and efficiency of wireless networks by enabling proactive resource allocation, interference mitigation, and improved quality of service.

Papers

February 27, 2024

QoS prediction in radio vehicular environments via prior user information
Noor Ul Ain, Rodrigo Hernangómez, Alexandros Palaios, Martin Kasparick, Sławomir Stańczak
Quality Prediction Radio Source Quality of Service Prediction User Data Radio Environment

November 30, 2023

Learning Radio Environments by Differentiable Ray Tracing
Jakob Hoydis, Fayçal Aït Aoudia, Sebastian Cammerer, Florian Euchner, Merlin Nimier-David, Stephan ten Brink, Alexander Keller
Impulse Response Ray Tracing Differentiable Ray Radio Environment Channel Measurement

August 20, 2023

ProSpire: Proactive Spatial Prediction of Radio Environment Using Deep Learning
Shamik Sarkar, Dongning Guo, Danijela Cabric
Deep Learning Propagation Environment Spectrum Sharing Spatial Prediction Signal Strength Radio Environment

June 9, 2023

Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks
Pablo Soldati, Euhanna Ghadimi, Burak Demirel, Yu Wang, Raimundas Gaigalas, Mathias Sintorn
Artificial Intelligence Model Generalization Design Principle Wireless System Radio Environment

March 31, 2022

Differentially Private Federated Learning via Reconfigurable Intelligent Surface
Yuhan Yang, Yong Zhou, Youlong Wu, Yuanming Shi
Private Federated Learning Air Federated Learning Air Computation Reconfigurable Intelligent Surface Radio Environment

Radio Environment

Papers

QoS prediction in radio vehicular environments via prior user information

Learning Radio Environments by Differentiable Ray Tracing

ProSpire: Proactive Spatial Prediction of Radio Environment Using Deep Learning

Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks

Differentially Private Federated Learning via Reconfigurable Intelligent Surface