TBP: Temporal Beam Prediction for Mobile Millimeter-Wave Networks

• Published in: IEEE internet of things journal 2024-07, Vol.11 (14), p.24960-24972
• Main Authors: Zhang, Shichen, Yan, Qiben, Li, Tianxing, Xiao, Li, Zeng, Huacheng
• Format: Article
• Language: English
• Subjects: Antenna arrays; Antenna radiation patterns; Array signal processing; Beam steering; Beamforming; Channels; Communications systems; deep learning; Feature extraction; Indexes; Long short term memory; Millimeter wave communication; Millimeter waves; millimeter-wave (mmWave) communications; Training; Trajectory; Wireless networks
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2024.3390611

Beam selection is a fundamental problem in millimeter-wave (mmWave) communication systems. Yet, most existing beam selection techniques focus on the exploitation of spatial channel features to reduce their airtime overhead in stationary mmWave networks. In this article, we exploit the temporal correlation of wireless channels to facilitate beam selection in mobile mmWave networks. Specifically, we present a temporal beam prediction (TBP) scheme for a mobile mmWave device to predict its future beam direction based on its history beam selection profile. TBP has two challenges in its design: 1) nonuniform history data samples due to the bursty nature of data traffic and 2) nonsmooth beam angles over time due to the multipath effect of channels and the imperfect radiation pattern of phased-array antennas. TBP addresses these two challenges by employing a new mobility-aware LSTM model that takes data timestamp for its training, together with an adversarial learning model to exploit user-independent features for beam steering. We have evaluated TBP through over-the-air (OTA) experiments on a 60-GHz mmWave testbed. Experimental results show that the average prediction error of TBP is less than 7° and that TBP improves the throughput by 60% in representative mmWave networks.