Best Beam Prediction in Non-Standalone mm Wave Systems

Tushara Ponnada; Parham Kazemi; Hanan Al-Tous; Ying-Chang Liang; Olav Tirkkonen

doi:10.1109/EuCNC/6GSummit51104.2021.9482504

Best Beam Prediction in Non-Standalone mm Wave Systems

Tushara Ponnada, Parham Kazemi, Hanan Al-Tous, Ying-Chang Liang, Olav Tirkkonen

Communications Theory

University of Electronic Science and Technology of China

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

10 Citations (Scopus)

318 Downloads (Pure)

Abstract

We consider a machine learning approach to perform best beam prediction in Non-Standalone Millimeter Wave (mmWave) Systems utilizing Channel Charting (CC). The approach reduces communication overheads and delays associated
with initial access and beam tracking in 5G New Radio (NR) systems. The network has a mmWave and a sub-6 GHz component. We devise a Base Station (BS) centric approach for best mmWave beam prediction, based on Channel State Information (CSI) measured at the sub-6 GHz BS, with no need to exchange information with UEs. In a training phase, we collect CSI at the sub-6 GHz BS from sample UEs, and construct a dimensional reduction of the sample CSI, called a CC. We annotate the CC with best beam information measured at a mmWave BS for the sample UEs, assuming autonomous beamformer at the UE side. A beam predictor is trained based on this information, connecting any sub-6 GHz CSI with a predicted best mmWave beam. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetic spatially consistent CSI. With a neural network predictor, we obtain 91% accuracy for predicting best beam and 99% accuracy for predicting one of two best beams. The accuracy of CC based beam prediction is indistinguishable from true location based beam prediction.

Original language	English
Title of host publication	2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)
Publisher	IEEE
Pages	532-537
Number of pages	6
ISBN (Electronic)	978-1-6654-1526-2
DOIs	https://doi.org/10.1109/EuCNC/6GSummit51104.2021.9482504
Publication status	Published - 28 Jul 2021
MoE publication type	A4 Conference publication
Event	European Conference on Networks and Communications - Porto, Portugal Duration: 8 Jun 2021 → 11 Jun 2021

Publication series

Name	European conference on networks and communications
ISSN (Print)	2475-6490
ISSN (Electronic)	2575-4912

Conference

Conference	European Conference on Networks and Communications
Abbreviated title	EuCNC
Country/Territory	Portugal
City	Porto
Period	08/06/2021 → 11/06/2021

Keywords

Non-Standalone systems
beam prediction
channel charting
network centric approach
radio resource management

Access to Document

10.1109/EuCNC/6GSummit51104.2021.9482504

Ponnada_Best_Beam_Prediction_in_Non-Standalone_mmWave_SystemsAccepted author manuscript, 1.45 MB

Cite this

Ponnada, T., Kazemi, P., Al-Tous, H., Liang, Y.-C., & Tirkkonen, O. (2021). Best Beam Prediction in Non-Standalone mm Wave Systems. In 2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) (pp. 532-537). Article 9482504 (European conference on networks and communications). IEEE. https://doi.org/10.1109/EuCNC/6GSummit51104.2021.9482504

@inproceedings{c41eb3acc0894b6c8f6775158921353c,

title = "Best Beam Prediction in Non-Standalone mm Wave Systems",

abstract = "We consider a machine learning approach to perform best beam prediction in Non-Standalone Millimeter Wave (mmWave) Systems utilizing Channel Charting (CC). The approach reduces communication overheads and delays associated with initial access and beam tracking in 5G New Radio (NR) systems. The network has a mmWave and a sub-6 GHz component. We devise a Base Station (BS) centric approach for best mmWave beam prediction, based on Channel State Information (CSI) measured at the sub-6 GHz BS, with no need to exchange information with UEs. In a training phase, we collect CSI at the sub-6 GHz BS from sample UEs, and construct a dimensional reduction of the sample CSI, called a CC. We annotate the CC with best beam information measured at a mmWave BS for the sample UEs, assuming autonomous beamformer at the UE side. A beam predictor is trained based on this information, connecting any sub-6 GHz CSI with a predicted best mmWave beam. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetic spatially consistent CSI. With a neural network predictor, we obtain 91\% accuracy for predicting best beam and 99\% accuracy for predicting one of two best beams. The accuracy of CC based beam prediction is indistinguishable from true location based beam prediction.",

keywords = "Non-Standalone systems, beam prediction, channel charting, network centric approach, radio resource management",

author = "Tushara Ponnada and Parham Kazemi and Hanan Al-Tous and Ying-Chang Liang and Olav Tirkkonen",

note = "| openaire: EC/H2020/813999/EU//WINDMILL; European Conference on Networks and Communications, EuCNC ; Conference date: 08-06-2021 Through 11-06-2021",

year = "2021",

month = jul,

day = "28",

doi = "10.1109/EuCNC/6GSummit51104.2021.9482504",

language = "English",

series = "European conference on networks and communications",

publisher = "IEEE",

pages = "532--537",

booktitle = "2021 Joint European Conference on Networks and Communications \& 6G Summit (EuCNC/6G Summit)",

address = "United States",

}

Ponnada, T, Kazemi, P, Al-Tous, H, Liang, Y-C & Tirkkonen, O 2021, Best Beam Prediction in Non-Standalone mm Wave Systems. in 2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)., 9482504, European conference on networks and communications, IEEE, pp. 532-537, European Conference on Networks and Communications, Porto, Portugal, 08/06/2021. https://doi.org/10.1109/EuCNC/6GSummit51104.2021.9482504

Best Beam Prediction in Non-Standalone mm Wave Systems. / Ponnada, Tushara; Kazemi, Parham; Al-Tous, Hanan et al.
2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). IEEE, 2021. p. 532-537 9482504 (European conference on networks and communications).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Best Beam Prediction in Non-Standalone mm Wave Systems

AU - Ponnada, Tushara

AU - Kazemi, Parham

AU - Al-Tous, Hanan

AU - Liang, Ying-Chang

AU - Tirkkonen, Olav

N1 - | openaire: EC/H2020/813999/EU//WINDMILL

PY - 2021/7/28

Y1 - 2021/7/28

N2 - We consider a machine learning approach to perform best beam prediction in Non-Standalone Millimeter Wave (mmWave) Systems utilizing Channel Charting (CC). The approach reduces communication overheads and delays associated with initial access and beam tracking in 5G New Radio (NR) systems. The network has a mmWave and a sub-6 GHz component. We devise a Base Station (BS) centric approach for best mmWave beam prediction, based on Channel State Information (CSI) measured at the sub-6 GHz BS, with no need to exchange information with UEs. In a training phase, we collect CSI at the sub-6 GHz BS from sample UEs, and construct a dimensional reduction of the sample CSI, called a CC. We annotate the CC with best beam information measured at a mmWave BS for the sample UEs, assuming autonomous beamformer at the UE side. A beam predictor is trained based on this information, connecting any sub-6 GHz CSI with a predicted best mmWave beam. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetic spatially consistent CSI. With a neural network predictor, we obtain 91% accuracy for predicting best beam and 99% accuracy for predicting one of two best beams. The accuracy of CC based beam prediction is indistinguishable from true location based beam prediction.

AB - We consider a machine learning approach to perform best beam prediction in Non-Standalone Millimeter Wave (mmWave) Systems utilizing Channel Charting (CC). The approach reduces communication overheads and delays associated with initial access and beam tracking in 5G New Radio (NR) systems. The network has a mmWave and a sub-6 GHz component. We devise a Base Station (BS) centric approach for best mmWave beam prediction, based on Channel State Information (CSI) measured at the sub-6 GHz BS, with no need to exchange information with UEs. In a training phase, we collect CSI at the sub-6 GHz BS from sample UEs, and construct a dimensional reduction of the sample CSI, called a CC. We annotate the CC with best beam information measured at a mmWave BS for the sample UEs, assuming autonomous beamformer at the UE side. A beam predictor is trained based on this information, connecting any sub-6 GHz CSI with a predicted best mmWave beam. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetic spatially consistent CSI. With a neural network predictor, we obtain 91% accuracy for predicting best beam and 99% accuracy for predicting one of two best beams. The accuracy of CC based beam prediction is indistinguishable from true location based beam prediction.

KW - Non-Standalone systems

KW - beam prediction

KW - channel charting

KW - network centric approach

KW - radio resource management

UR - https://www.scopus.com/pages/publications/85112661266

U2 - 10.1109/EuCNC/6GSummit51104.2021.9482504

DO - 10.1109/EuCNC/6GSummit51104.2021.9482504

M3 - Conference article in proceedings

T3 - European conference on networks and communications

SP - 532

EP - 537

BT - 2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)

PB - IEEE

T2 - European Conference on Networks and Communications

Y2 - 8 June 2021 through 11 June 2021

ER -

Best Beam Prediction in Non-Standalone mm Wave Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

WINDMILL: Integrating Wireless Communication ENgineering and MachIne Learning

-: Radio Network Optimization for Heterogeneous Machine Connectivity

Science-IT

Cite this

Best Beam Prediction in Non-Standalone mm Wave Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

WINDMILL: Integrating Wireless Communication ENgineering and MachIne Learning

-: Radio Network Optimization for Heterogeneous Machine Connectivity

Equipment

Science-IT

Cite this