Beamwidth Optimization for 5G NR Millimeter Wave Cellular Networks: A Multi-armed Bandit Approach

Feng, Mingjie; Akgun, Berk; Aykin, Irmak; Krunz, Marwan

doi:10.1109/icc42927.2021.9500381

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Please see [5], [6], [7] and the references therein. More recent examples further include selecting the optimal beamwidth for beam training in [8] and our prior work [2]. Prior work has shown how MAB can improve cumulative system throughput compared to reasonable nonsequential solutions.…”

Section: Introductionmentioning

confidence: 99%

Multi-Armed Bandit for Link Configuration in Millimeter-Wave Networks: An Approach for Solving Sequential Decision-Making Problems

Zhang

Heath

2023

IEEE Veh. Technol. Mag.

View full text Add to dashboard Cite

stablishing and maintaining millimeter-wave (mm-wave) links are challenging due to the changing environment and the high sensibility of mmwave signals to user mobility and channel conditions. mm-Wave link configuration problems often involve a search for optimal system parameter(s) under environmental uncertainties from a finite set of alternatives that are supported by the system hardware and protocol. For example, beam sweeping aims at identifying the optimal beam(s) for data transmission from a discrete codebook. Selecting parameters such as the beam sweeping period and the beamwidth is crucial to achieving high overall system throughput. In this article, we motivate the use of the multi-armed bandit (MAB) framework to intelligently search out the optimal configuration when establishing the mm-wave links. MAB is a reinforcement learning framework that guides a decision maker to sequentially select one action from a set of actions. As an example, we show that within the MAB framework, the optimal beam sweeping period, beamwidth, and beam directions could be dynamically learned with samplecomputational-efficient bandit algorithms. We conclude by highlighting some future research directions on enhancing mm-wave link configuration design with MAB.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Armed Bandit for Link Configuration in Millimeter-Wave Networks: An Approach for Solving Sequential Decision-Making Problems

Zhang

Heath

2023

IEEE Veh. Technol. Mag.

View full text Add to dashboard Cite

show abstract

“…To address this, beamwidth adaptation has been proposed as a solution to optimize transmission in vehicular networks [9]. Recent studies have extensively explored the performance of beamwidth adaptation in vehicular networks, emphasizing its potential to cater to the unique challenges posed by vehicular environments [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

“…The work in [10] examines the challenges of using highly directional antennas in mmWave cellular net-works, particularly the need for precise beam alignment between a base station (BS) and user equipment (UE). The paper proposes an approach to improve the beam-sweeping process and reduce initial access (IA) delay, which is caused by the necessity to sweep over many directions due to the size of the beam.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

Manic,

Foh,

Kose

et al. 2023

2023 IEEE 16th Malaysia International Conference on Communication (MICC)

View full text Add to dashboard Cite

The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles, enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of different antenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies.

show abstract

Clustering Algorithm in Dense Millimeter Wave Heterogeneous Cellular Networks

2023

Wireless Pers Commun

View full text Add to dashboard Cite

Beamwidth Optimization for 5G NR Millimeter Wave Cellular Networks: A Multi-armed Bandit Approach

Cited by 8 publications

References 17 publications

Multi-Armed Bandit for Link Configuration in Millimeter-Wave Networks: An Approach for Solving Sequential Decision-Making Problems

Multi-Armed Bandit for Link Configuration in Millimeter-Wave Networks: An Approach for Solving Sequential Decision-Making Problems

Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

Clustering Algorithm in Dense Millimeter Wave Heterogeneous Cellular Networks

Contact Info

Product

Resources

About