Adaptive Beam Management in 5G-NR: A Machine Learning Perspective

Abstract

In this rapid era of technology, speed of communication has become an important factor. To overcome this challenge, 5G/NR technology is being explored. One of the ways of doing this is by using the so called millimeter wave spectrum. In order
to make usage of the mmWave spectrum, due to the high path loss it introduces,
the beamforming technique is adopted. Beamforming is a method used in high
frequency signal transmission for focusing or directing the beam towards the user
in such a way that it will improve the signal strength and throughput and reduce
the signal wastage, resulting in better experience. This can be achieved by constructively
adding the phase shift from each antenna element towards the desired
direction. Beam refinement or tracking, which are used in 5G/NR, are the mechanisms
that selects the active beam used for transmission between the base station
and User Equipment. Beam management is based on the continuous measurement
reports from the UE on the reference signals related to the available beams. With
higher frequencies and more narrow beams for coverage enhancements, beam management
is becoming increasingly important. However, it comes with a collective
cost due to the frequent measurements that are needed to monitor the positions
of all connected UEs.
The purpose of this Master’s thesis work is to investigate if machine learning
methods could be applied to optimize the beam measurements and find the most
efficient way to use these results to select the best beam for multiple UEs. This
will allow the UEs and Base Station (BS) to have a strong signal for better transmission.
We further compare the results obtained, with 3GPP baseline algorithm
to gain insights about its performance.

Popular Abstract

With the increasing demands on high data rates in the mobile industry, the fifth generation technology (5G) has now replaced the old fourth generation technology (4G) as the latest standard and solution for the mobile market. The high data rates growth in 5G is obtained from the high bandwidth in the mmWave frequency spectrum. But, this ultra high frequency causes the technical difficulty in terms of signal attenuation. The 5G offers advanced technologies to overcome this difficulty. One of them is called beamforming, which can agilely help transmitter (base station) focus and direct narrower beam onto the receiver (cell phone). Have the consideration of the mobility of cell phone, the base station needs to keep tracking the location of cell phone in order toa maintain good signal quality. Thus, the base station needs to keep updating the direction of narrow beams based on the channel measurements report from the moving cell phone.
The goal of this thesis is to select the narrow beam, which can maintain a good signal quality with moving cell phone. In this thesis, the beam selection has been done by the Machine learning algorithm. Machine learning algorithm can learn from the training of many data sets, and then it can be used to predict an expected result. In this thesis, the data sets for the training includes channel measurements values and corresponding narrow beam indexes. Then the machine learning predicts narrow beam indexes in different scenarios.
The performance brought by the Machine learning algorithm was compared with the existing algorithm (baseline). The result shows that Machine learning algorithm brings significant better performance in terms of throughput.

• author: Wang, Boqiang
• supervisor: Harsh Tataria
• organization: Department of Electrical and Information Technology
• course: EITM02 20201
• year: 2021
• type: H2 - Master's Degree (Two Years)
• subject: Technology and Engineering
• keywords: Machine Learning, Neural Network, Beam Management, Beam Tracking, mmWaves, 5G NR, Beamforming
• report number: LU/LTH-EIT 2021-807
• language: English
• id: 9042050
• date added to LUP: 2021-09-22 10:29:47
• date last changed: 2021-10-04 10:25:41