Deep learning coordinated beamforming for Highly-Mobile millimeter wave systems

Ahmed Alkhateeb, Sam Alex, Paul Varkey, Ying Li, Qi Qu, Djordje Tujkovic

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Supporting high mobility in millimeter wave (mmWave) systems enables a wide range of important applications, such as vehicular communications and wireless virtual/augmented reality. Realizing this in practice, though, requires overcoming several challenges. First, the use of narrow beams and the sensitivity of mmWave signals to blockage greatly impact the coverage and reliability of highly-mobile links. Second, highly-mobile users in dense mmWave deployments need to frequently hand-off between base stations (BSs), which is associated with critical control and latency overhead. Furthermore, identifying the optimal beamforming vectors in large antenna array mmWave systems requires considerable training overhead, which significantly affects the efficiency of these mobile systems. In this paper, a novel integrated machine learning and coordinated beamforming solution is developed to overcome these challenges and enable highly-mobile mmWave applications. In the proposed solution, a number of distributed yet coordinating BSs simultaneously serve a mobile user. This user ideally needs to transmit only one uplink training pilot sequence that will be jointly received at the coordinating BSs using omni or quasi-omni beam patterns. These received signals draw a defining signature not only for the user location, but also for its interaction with the surrounding environment. The developed solution then leverages a deep learning model that learns how to use these signatures to predict the beamforming vectors at the BSs. This renders a comprehensive solution that supports highly mobile mmWave applications with reliable coverage, low latency, and negligible training overhead. Extensive simulation results based on accurate ray-tracing, show that the proposed deep-learning coordinated beamforming strategy approaches the achievable rate of the genie-aided solution that knows the optimal beamforming vectors with no training overhead. Compared with traditional beamforming solutions, the results show that the proposed deep learning-based strategy attains higher rates, especially in high-mobility large-array regimes.

Original languageEnglish (US)
Pages (from-to)37328-37348
Number of pages21
JournalIEEE Access
Volume6
DOIs
StatePublished - Jan 1 2018

Fingerprint

Beamforming
Millimeter waves
Base stations
Augmented reality
Ray tracing
Antenna arrays
Telecommunication links
Learning systems
Deep learning
Communication

Keywords

  • beamforming
  • channel estimation
  • deep learning
  • machine learning
  • Millimeter wave
  • vehicular communications
  • wireless virtual/augmented reality

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Deep learning coordinated beamforming for Highly-Mobile millimeter wave systems. / Alkhateeb, Ahmed; Alex, Sam; Varkey, Paul; Li, Ying; Qu, Qi; Tujkovic, Djordje.

In: IEEE Access, Vol. 6, 01.01.2018, p. 37328-37348.

Research output: Contribution to journalArticle

Alkhateeb, Ahmed ; Alex, Sam ; Varkey, Paul ; Li, Ying ; Qu, Qi ; Tujkovic, Djordje. / Deep learning coordinated beamforming for Highly-Mobile millimeter wave systems. In: IEEE Access. 2018 ; Vol. 6. pp. 37328-37348.
@article{b83bda664db94aac9f1025cbbaffaa78,
title = "Deep learning coordinated beamforming for Highly-Mobile millimeter wave systems",
abstract = "Supporting high mobility in millimeter wave (mmWave) systems enables a wide range of important applications, such as vehicular communications and wireless virtual/augmented reality. Realizing this in practice, though, requires overcoming several challenges. First, the use of narrow beams and the sensitivity of mmWave signals to blockage greatly impact the coverage and reliability of highly-mobile links. Second, highly-mobile users in dense mmWave deployments need to frequently hand-off between base stations (BSs), which is associated with critical control and latency overhead. Furthermore, identifying the optimal beamforming vectors in large antenna array mmWave systems requires considerable training overhead, which significantly affects the efficiency of these mobile systems. In this paper, a novel integrated machine learning and coordinated beamforming solution is developed to overcome these challenges and enable highly-mobile mmWave applications. In the proposed solution, a number of distributed yet coordinating BSs simultaneously serve a mobile user. This user ideally needs to transmit only one uplink training pilot sequence that will be jointly received at the coordinating BSs using omni or quasi-omni beam patterns. These received signals draw a defining signature not only for the user location, but also for its interaction with the surrounding environment. The developed solution then leverages a deep learning model that learns how to use these signatures to predict the beamforming vectors at the BSs. This renders a comprehensive solution that supports highly mobile mmWave applications with reliable coverage, low latency, and negligible training overhead. Extensive simulation results based on accurate ray-tracing, show that the proposed deep-learning coordinated beamforming strategy approaches the achievable rate of the genie-aided solution that knows the optimal beamforming vectors with no training overhead. Compared with traditional beamforming solutions, the results show that the proposed deep learning-based strategy attains higher rates, especially in high-mobility large-array regimes.",
keywords = "beamforming, channel estimation, deep learning, machine learning, Millimeter wave, vehicular communications, wireless virtual/augmented reality",
author = "Ahmed Alkhateeb and Sam Alex and Paul Varkey and Ying Li and Qi Qu and Djordje Tujkovic",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2850226",
language = "English (US)",
volume = "6",
pages = "37328--37348",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Deep learning coordinated beamforming for Highly-Mobile millimeter wave systems

AU - Alkhateeb, Ahmed

AU - Alex, Sam

AU - Varkey, Paul

AU - Li, Ying

AU - Qu, Qi

AU - Tujkovic, Djordje

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Supporting high mobility in millimeter wave (mmWave) systems enables a wide range of important applications, such as vehicular communications and wireless virtual/augmented reality. Realizing this in practice, though, requires overcoming several challenges. First, the use of narrow beams and the sensitivity of mmWave signals to blockage greatly impact the coverage and reliability of highly-mobile links. Second, highly-mobile users in dense mmWave deployments need to frequently hand-off between base stations (BSs), which is associated with critical control and latency overhead. Furthermore, identifying the optimal beamforming vectors in large antenna array mmWave systems requires considerable training overhead, which significantly affects the efficiency of these mobile systems. In this paper, a novel integrated machine learning and coordinated beamforming solution is developed to overcome these challenges and enable highly-mobile mmWave applications. In the proposed solution, a number of distributed yet coordinating BSs simultaneously serve a mobile user. This user ideally needs to transmit only one uplink training pilot sequence that will be jointly received at the coordinating BSs using omni or quasi-omni beam patterns. These received signals draw a defining signature not only for the user location, but also for its interaction with the surrounding environment. The developed solution then leverages a deep learning model that learns how to use these signatures to predict the beamforming vectors at the BSs. This renders a comprehensive solution that supports highly mobile mmWave applications with reliable coverage, low latency, and negligible training overhead. Extensive simulation results based on accurate ray-tracing, show that the proposed deep-learning coordinated beamforming strategy approaches the achievable rate of the genie-aided solution that knows the optimal beamforming vectors with no training overhead. Compared with traditional beamforming solutions, the results show that the proposed deep learning-based strategy attains higher rates, especially in high-mobility large-array regimes.

AB - Supporting high mobility in millimeter wave (mmWave) systems enables a wide range of important applications, such as vehicular communications and wireless virtual/augmented reality. Realizing this in practice, though, requires overcoming several challenges. First, the use of narrow beams and the sensitivity of mmWave signals to blockage greatly impact the coverage and reliability of highly-mobile links. Second, highly-mobile users in dense mmWave deployments need to frequently hand-off between base stations (BSs), which is associated with critical control and latency overhead. Furthermore, identifying the optimal beamforming vectors in large antenna array mmWave systems requires considerable training overhead, which significantly affects the efficiency of these mobile systems. In this paper, a novel integrated machine learning and coordinated beamforming solution is developed to overcome these challenges and enable highly-mobile mmWave applications. In the proposed solution, a number of distributed yet coordinating BSs simultaneously serve a mobile user. This user ideally needs to transmit only one uplink training pilot sequence that will be jointly received at the coordinating BSs using omni or quasi-omni beam patterns. These received signals draw a defining signature not only for the user location, but also for its interaction with the surrounding environment. The developed solution then leverages a deep learning model that learns how to use these signatures to predict the beamforming vectors at the BSs. This renders a comprehensive solution that supports highly mobile mmWave applications with reliable coverage, low latency, and negligible training overhead. Extensive simulation results based on accurate ray-tracing, show that the proposed deep-learning coordinated beamforming strategy approaches the achievable rate of the genie-aided solution that knows the optimal beamforming vectors with no training overhead. Compared with traditional beamforming solutions, the results show that the proposed deep learning-based strategy attains higher rates, especially in high-mobility large-array regimes.

KW - beamforming

KW - channel estimation

KW - deep learning

KW - machine learning

KW - Millimeter wave

KW - vehicular communications

KW - wireless virtual/augmented reality

UR - http://www.scopus.com/inward/record.url?scp=85049100664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049100664&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2850226

DO - 10.1109/ACCESS.2018.2850226

M3 - Article

VL - 6

SP - 37328

EP - 37348

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -