@ARTICLE{Mohamed_Ehab_Mahmoud_Millimeter_2021,
 author={Mohamed, Ehab Mahmoud},
 volume={vol. 67},
 number={No 1},
 journal={International Journal of Electronics and Telecommunications},
 pages={95-102},
 howpublished={online},
 year={2021},
 publisher={Polish Academy of Sciences Committee of Electronics and Telecommunications},
 abstract={Beamforming training (BT) is considered as an essential process to accomplish the communications in the millimeter wave (mmWave) band, i.e., 30 ~ 300 GHz. This process aims to find out the best transmit/receive antenna beams to compensate the impairments of the mmWave channel and successfully establish the mmWave link. Typically, the mmWave BT process is highly-time consuming affecting the overall throughput and energy consumption of the mmWave link establishment. In this paper, a machine learning (ML) approach, specifically reinforcement learning (RL), is utilized for enabling the mmWave BT process by modeling it as a multi-armed bandit (MAB) problem with the aim of maximizing the long-term throughput of the constructed mmWave link. Based on this formulation, MAB algorithms such as upper confidence bound (UCB), Thompson sampling (TS), epsilon-greedy (e-greedy), are utilized to address the problem and accomplish the mmWave BT process. Numerical simulations confirm the superior performance of the proposed MAB approach over the existing mmWave BT techniques.},
 type={Article},
 title={Millimeter Wave Beamforming Training: A Reinforcement Learning Approach},
 URL={http://journals.pan.pl/Content/118870/PDF/13_2710_Mohamed_sk.pdf},
 doi={10.24425/ijet.2021.135949},
 keywords={millimeter wave, beamforming training, multiarmed bandit, reinforcement learning},
}