TY - GEN
T1 - Radar Aided 6G Beam Prediction
T2 - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
AU - Demirhan, Umut
AU - Alkhateeb, Ahmed
N1 - Funding Information:
VII. ACKNOWLEDGEMENT This work is supported by the National Science Foundation under Grant No. 2048021.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Adjusting the narrow beams at millimeter wave (mmWave) and terahertz (THz) MIMO communication systems is associated with high beam training overhead, which makes it hard for these systems to support highly-mobile applications. This overhead can potentially be reduced or eliminated if sufficient awareness about the transmitter/receiver locations and the surrounding environment is available. In this paper, efficient deep learning solutions that leverage radar sensory data are developed to guide the mmWave beam prediction and significantly reduce the beam training overhead. Our solutions integrate radar signal processing approaches to extract the relevant features for the learning models, and hence optimize their complexity and inference time. The proposed machine learning based radar-aided beam prediction solutions are evaluated using a large-scale real-world mmWave radar/communication dataset and their capabilities were demonstrated in a realistic vehicular communication scenario. In addition to completely eliminating the radar/communication calibration overhead, the proposed algorithms are able to achieve around 90% top-5 beam prediction accuracy while saving 93% of the beam training overhead. This highlights a promising direction for addressing the training overhead challenge in mmWave/THz communication systems.
AB - Adjusting the narrow beams at millimeter wave (mmWave) and terahertz (THz) MIMO communication systems is associated with high beam training overhead, which makes it hard for these systems to support highly-mobile applications. This overhead can potentially be reduced or eliminated if sufficient awareness about the transmitter/receiver locations and the surrounding environment is available. In this paper, efficient deep learning solutions that leverage radar sensory data are developed to guide the mmWave beam prediction and significantly reduce the beam training overhead. Our solutions integrate radar signal processing approaches to extract the relevant features for the learning models, and hence optimize their complexity and inference time. The proposed machine learning based radar-aided beam prediction solutions are evaluated using a large-scale real-world mmWave radar/communication dataset and their capabilities were demonstrated in a realistic vehicular communication scenario. In addition to completely eliminating the radar/communication calibration overhead, the proposed algorithms are able to achieve around 90% top-5 beam prediction accuracy while saving 93% of the beam training overhead. This highlights a promising direction for addressing the training overhead challenge in mmWave/THz communication systems.
UR - http://www.scopus.com/inward/record.url?scp=85130679688&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130679688&partnerID=8YFLogxK
U2 - 10.1109/WCNC51071.2022.9771564
DO - 10.1109/WCNC51071.2022.9771564
M3 - Conference contribution
AN - SCOPUS:85130679688
T3 - IEEE Wireless Communications and Networking Conference, WCNC
SP - 2655
EP - 2660
BT - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 10 April 2022 through 13 April 2022
ER -