Drive Test Minimization Using Deep Learning with Bayesian Approximation

Jakob Thrane; Matteo Artuso; Darko Zibar; Henrik Lehrmann Christiansen

doi:10.1109/VTCFall.2018.8690911

Drive Test Minimization Using Deep Learning with Bayesian Approximation

Jakob Thrane, Matteo Artuso, Darko Zibar, Henrik Lehrmann Christiansen

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

Abstract

Drive testing is a common practice performed by operators to optimize and evaluate their mobile networks with respect to capacity and coverage. For dense areas, drive test measurements are very time-consuming due to many obstacles causing Non-Line-Of-Sight (NLoS) scenarios. In this paper, we show how Deep Learning (DL) techniques can be utilized to predict LTE signal quality metrics using drive test measurements. Moreover, we show how the obtained solution can offer insight into where additional measurements are required. The proposed solution can accurately predict LTE signal quality metrics reducing drive tests needed by up to 70%.

Original language	English
Title of host publication	Proceedings of 2018 IEEE 88th Vehicular Technology Conference
Number of pages	5
Publisher	IEEE
Publication date	2018
Pages	1-5
ISBN (Print)	9781538663585
DOIs	https://doi.org/10.1109/VTCFall.2018.8690911
Publication status	Published - 2018
Event	2018 IEEE 88th Vehicular Technology Conference - Hilton Chicago, Chicago, United States Duration: 27 Aug 2018 → 30 Aug 2018 Conference number: 88 http://www.ieeevtc.org/vtc2018fall/

Conference

Conference	2018 IEEE 88th Vehicular Technology Conference
Number	88
Location	Hilton Chicago
Country/Territory	United States
City	Chicago
Period	27/08/2018 → 30/08/2018
Internet address	http://www.ieeevtc.org/vtc2018fall/

Keywords

Communication channels
Channel models
Machine Learning
4G mobile communication

Access to Document

10.1109/VTCFall.2018.8690911

OpenUrl availability

Full text

Cite this

@inproceedings{42629c9ff3544fa9b5bc5a516e76343a,

title = "Drive Test Minimization Using Deep Learning with Bayesian Approximation",

abstract = "Drive testing is a common practice performed by operators to optimize and evaluate their mobile networks with respect to capacity and coverage. For dense areas, drive test measurements are very time-consuming due to many obstacles causing Non-Line-Of-Sight (NLoS) scenarios. In this paper, we show how Deep Learning (DL) techniques can be utilized to predict LTE signal quality metrics using drive test measurements. Moreover, we show how the obtained solution can offer insight into where additional measurements are required. The proposed solution can accurately predict LTE signal quality metrics reducing drive tests needed by up to 70%.",

keywords = "Communication channels, Channel models, Machine Learning, 4G mobile communication",

author = "Jakob Thrane and Matteo Artuso and Darko Zibar and Christiansen, {Henrik Lehrmann}",

year = "2018",

doi = "10.1109/VTCFall.2018.8690911",

language = "English",

isbn = "9781538663585 ",

pages = "1--5",

booktitle = "Proceedings of 2018 IEEE 88th Vehicular Technology Conference",

publisher = "IEEE",

address = "United States",

note = "2018 IEEE 88th Vehicular Technology Conference, VTC2018-Fall ; Conference date: 27-08-2018 Through 30-08-2018",

url = "http://www.ieeevtc.org/vtc2018fall/",

}

TY - GEN

T1 - Drive Test Minimization Using Deep Learning with Bayesian Approximation

AU - Thrane, Jakob

AU - Artuso, Matteo

AU - Zibar, Darko

AU - Christiansen, Henrik Lehrmann

N1 - Conference code: 88

PY - 2018

Y1 - 2018

N2 - Drive testing is a common practice performed by operators to optimize and evaluate their mobile networks with respect to capacity and coverage. For dense areas, drive test measurements are very time-consuming due to many obstacles causing Non-Line-Of-Sight (NLoS) scenarios. In this paper, we show how Deep Learning (DL) techniques can be utilized to predict LTE signal quality metrics using drive test measurements. Moreover, we show how the obtained solution can offer insight into where additional measurements are required. The proposed solution can accurately predict LTE signal quality metrics reducing drive tests needed by up to 70%.

AB - Drive testing is a common practice performed by operators to optimize and evaluate their mobile networks with respect to capacity and coverage. For dense areas, drive test measurements are very time-consuming due to many obstacles causing Non-Line-Of-Sight (NLoS) scenarios. In this paper, we show how Deep Learning (DL) techniques can be utilized to predict LTE signal quality metrics using drive test measurements. Moreover, we show how the obtained solution can offer insight into where additional measurements are required. The proposed solution can accurately predict LTE signal quality metrics reducing drive tests needed by up to 70%.

KW - Communication channels

KW - Channel models

KW - Machine Learning

KW - 4G mobile communication

U2 - 10.1109/VTCFall.2018.8690911

DO - 10.1109/VTCFall.2018.8690911

M3 - Article in proceedings

SN - 9781538663585

SP - 1

EP - 5

BT - Proceedings of 2018 IEEE 88th Vehicular Technology Conference

PB - IEEE

T2 - 2018 IEEE 88th Vehicular Technology Conference

Y2 - 27 August 2018 through 30 August 2018

ER -

Drive Test Minimization Using Deep Learning with Bayesian Approximation

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this