2018/07/07 by Ahmed Alkhateeb, Alkhateeb, Ahmed, Iz Beltagy +1 · 3 citations
Engineering · #Millimeter-Wave Propagation and Modeling #Advanced MIMO Systems Optimization #Microwave Engineering and Waveguides
paper · pdf · doi:10.48550/arxiv.1807.02723
The sensitivity of millimeter wave (mmWave) signals to blockages is a\nfundamental challenge for mobile mmWave communication systems. The sudden\nblockage of the line-of-sight (LOS) link between the base station and the\nmobile user normally leads to disconnecting the communication session, which\nhighly impacts the system reliability. Further, reconnecting the user to\nanother LOS base station incurs high beam training overhead and critical\nlatency problems. In this paper, we leverage machine learning tools and propose\na novel solution for these reliability and latency challenges in mmWave MIMO\nsystems. In the developed solution, the base stations learn how to predict that\na certain link will experience blockage in the next few time frames using their\npast observations of adopted beamforming vectors. This allows the serving base\nstation to proactively hand-over the user to another base station with a highly\nprobable LOS link. Simulation results show that the developed deep learning\nbased strategy successfully predicts blockage/hand-off in close to 95% of the\ntimes. This reduces the probability of communication session disconnection,\nwhich ensures high reliability and low latency in mobile mmWave systems.\n