Home // International Journal On Advances in Telecommunications, volume 13, numbers 1 and 2, 2020 // View article

AI Based Beam Management for 5G (mmWave) at Wireless Edge

Authors:
Chitwan Arora
Abheek Saha

Keywords: mmWave; beam shaping; machine learning; double directional channel ; wireless edge.

Abstract:
Fast and accurate beam shaping mechanism is the key enabler in the use of millimeter-wave in the 5th Generation cellular systems in order to achieve low latency and high data rate requirements. Recent advances in Deep Learning (DL) has shown that Deep Learning (DL) based techniques can play a significant role in efficient beam shaping. For effective operation, it is essential that the ML based beam management algorithm should be deployed at the place in network where all the relevant input parameters needed for beam management are available continuously as well as the output of the beam management can be applied instantly. In this paper, we shall demonstrate how an edge-based Deep Learning program can be used to implement adaptive mm-wave beam-shaping, so as to optimally use millimeter wave channels.

Pages: 10 to 20

Copyright: Copyright (c) to authors, 2020. Used with permission.

Publication date: June 30, 2020

Published in: journal

ISSN: 1942-2601