Machine Learning for Beam Alignment in Millimeter Wave Massive MIMO

Ma, Wenyan; Qi, Chenhao; Li, Geoffrey Ye

doi:10.1109/lwc.2020.2973972

Cited by 61 publications

(41 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the latency performance of mmWave networks for industrial automation, the authors of [31] proposed an adaptive beam selection strategy to select the best set of beams among multiple users to reduce the overall latency for all users. The authors of [32] studied the beam alignment problem of multiuser mmWave massive Multi-input Multi-output (MIMO) system and proposed an alignment algorithm with partial beams by using machine learning. The authors of [33] proposed an efficient hierarchical beamforming training mechanism to establish directional links in dense mmWave cellular networks.…”

Section: Mmwave Beam Managementmentioning

confidence: 99%

Network Capacity Optimization for Cellular‐Assisted Vehicular Systems by Online Learning‐Based mmWave Beam Selection

Gui

Liu

Deng

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Directional communication is helpful to improve the performance of millimeter Wave (mmWave) links. However, the dynamic nature of vehicular scenarios raises the complexity of directional mmWave vehicular communications. Also, a mmWave link is susceptible to blockages. Therefore, a mmWave vehicular communication system requires high environmental adaptability and context-awareness. Due to inadequate context information and insufficient beam settings in the existing related algorithm, it is difficult to pick out the set of beams with more reasonable widths and directions, which hinders the further promotion of network capacity in vehicular networks. Therefore, we propose an improved fast machine learning (IFML) algorithm to overcome this shortcoming. In order to improve network capacity while suppressing the additional beam search overhead, a partitioned search method is designed in the IFML. Also, in order to be robust to occasional fluctuations and timely adapt to significant changes in communication environments, the IFML adopts a flexible beam performance update approach based on adjustable weight coefficient. The simulation results show that the IFML significantly outperforms the existing related algorithm in terms of aggregate received data after a certain number of online learning time periods.

show abstract

Section: Mmwave Beam Managementmentioning

confidence: 99%

Network Capacity Optimization for Cellular‐Assisted Vehicular Systems by Online Learning‐Based mmWave Beam Selection

Gui

Liu

Deng

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Eq. ( 46) can be further solved by following the same steps as in ( 39)- (42). Therefore, the final simplified expression is given as…”

Section: Appendix F Proof Of Theorem 10mentioning

confidence: 99%

Design and Analysis of Aerial-Terrestrial Network: A Joint Solution for Coverage and Rate

et al. 2021

View full text Add to dashboard Cite

The exploitation of aerial base stations (A-BSs) in conjunction with terrestrial base stations (T-BSs) is envisioned as a promising solution to provide connectivity to devices and user-equipment (UE) in crowded situations (viz. in the sports event) and emergency situations (viz. in the disaster management). However, the use of A-BSs with existing terrestrial networks intensifies the inter-cell interference (ICI) to the devices and UEs, therefore leading to a degraded signal-to-interference-ratio (SIR). This paper addresses this issue by exploiting different radio access technology (RAT) (mmWave/microwave) for aerial and terrestrial networks. Indeed, the network connectivity is always a top priority for all applications. However, there are also some applications such as remote patient monitoring, and remote working, which requires both coverage and high data-rates. But, most of the existing research claims the trade-off between the coverage and the data-rate performance. Whereas this paper aims to improve coverage and rate simultaneously in an aerial-terrestrial networks by employing an optimal combination of mmWave and microwave RAT based on the proposed association strategy. The essential analysis of such an integrated network involves the evaluation of parameters based on the analytic model. Hence, this paper analytically obtains the coverage probability (CP) and average rate expressions for the proposed integrated aerial-terrestrial networks. The analysis is supported by probabilistic models-based simulations that agree closely with analytical results. The results claim that the proposed model leads to improved performance in terms of both CP and average rate. Also, the paper provides parametric analysis for CP and rate with A-BSs height and A-BSs density to enable its practical implementation in 5G/6G technologies.INDEX TERMS Aerial-terrestrial networks, millimeter-wave RAT, microwave RAT, coverage probability, average rate, stochastic geometry.

show abstract

“…In (8), j=1, …, n. After choosing the n beam-power pairs from each sector respectively, the EFML scheme will reselect no more than n beam-power pairs from all the chosen beam-power pairs of all the sectors, as described in the lines 8-18 in Algorithm 1. After this, the EFML scheme observes the received data of each vehicle group , with the context , ∈ , ∈ Ο in each beam-power < , , , > , and estimates the energy efficiency of each vehicle group , according to the formula (1) (see lines 2-3 in Algorithm 3).…”

Section: The Energy Efficiency-based Fmlmentioning

confidence: 99%

“…End if 16 Select < ,1 , ,1 >, …, < , , , > as the beam-power pairs <̂1 ,Gℋ ( ),̂1 ,Gℋ ( ) >, …, <̂, Gℋ ( ),̂, Gℋ ( ) > from (8) and then add them to ℬΡ Gℋ ( ) 17:…”

mentioning

confidence: 99%

Enhancing Energy Efficiency for Cellular-Assisted Vehicular Networks by Online Learning-Based mmWave Beam Selection

Gui

Liu

2021

Preprint

View full text Add to dashboard Cite

Millimeter-Wave (mmWave) technology is deemed as a feasible approach for future vehicular communications. However, mmWave signals are characterized by high path loss and penetration loss, which can be alleviated by directional communication. Directional transmission performance depends on beam alignment between transmitter and receiver, which is not easy to achieve in highly dynamic vehicular communications. The existing works addressed beam alignment problem by designing online learning-based mmWave beam selection schemes, which can be well adapted to high dynamic vehicular scenarios. However, this type of works does not take energy efficiency into account. Therefore, we propose an Energy efficiency-based FML (EFML) scheme to compensate for this shortfall, where the power consumption can be reduced as far as possible under the premise of meeting the basic data rate requirements of vehicle users and the users requesting the same content in close proximity can be organized into the same receiving group to share the same mmWave beam. The simulation results show that the EFML scheme improves both the network energy efficiency and the amount data of cellular-assisted vehicular networks at the cost of more beam performance update overhead. However, there is no difference in the cost of updating beam performance after adequate online learning.

show abstract

Machine Learning for Beam Alignment in Millimeter Wave Massive MIMO

Cited by 61 publications

References 11 publications

Network Capacity Optimization for Cellular‐Assisted Vehicular Systems by Online Learning‐Based mmWave Beam Selection

Network Capacity Optimization for Cellular‐Assisted Vehicular Systems by Online Learning‐Based mmWave Beam Selection

Design and Analysis of Aerial-Terrestrial Network: A Joint Solution for Coverage and Rate

Enhancing Energy Efficiency for Cellular-Assisted Vehicular Networks by Online Learning-Based mmWave Beam Selection

Contact Info

Product

Resources

About