Novel UE RF condition estimation algorithm by integrating machine learning

Yupu Dong, Zhenni Pan, Mohamad Erick Ernawan, Jiang Liu, Shigeru Shimamoto, Ragil Putro Wicaksono, Seiji Kunishige, Kwangrok Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

By 2020, 5G era will be commercially available. The smart city construction will also make great progress. Compared to current situation, more than thousand times of devices will connect to the cellular networks. For the operators, in order to analyze overall network performance, it is a key factor to estimate the user equipment (UE) radio frequency (RF) condition. However, practical RF estimation scheme is based on UE data log which can only observe UE that is at the top-serving cell with good RF condition. However, according to the comparison of actual UE data log and the scanner data log, potential RF problems may still exist since the UE will not always be served by the top-1 cell. In this paper, we propose a novel estimation scheme by integrating machine learning (ML) algorithm to analyze the scanner data logs from the target estimation zones where the mobility problems may occur. A hypothesis is obtained from learning step by various kinds of RF condition as input features. The numerical results show that the proposed estimation algorithm integrated ML can estimate probability of the potential mobility problems accurately.

Original languageEnglish
Title of host publicationMobile and Wireless Technologies 2017 - ICMWT 2017
PublisherSpringer Verlag
Pages102-113
Number of pages12
Volume425
ISBN (Print)9789811052804
DOIs
Publication statusPublished - 2018
Event4th iCatse Conference on Mobile and Wireless Technology, ICMWT 2017 - Kuala Lumpur, Malaysia
Duration: 2017 Jun 262017 Jun 29

Publication series

NameLecture Notes in Electrical Engineering
Volume425
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other4th iCatse Conference on Mobile and Wireless Technology, ICMWT 2017
CountryMalaysia
CityKuala Lumpur
Period17/6/2617/6/29

Fingerprint

Radio equipment
Learning systems
Frequency estimation
Network performance
Learning algorithms

Keywords

  • Estimation
  • Machine learning
  • Mobility problem
  • RF condition

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Dong, Y., Pan, Z., Ernawan, M. E., Liu, J., Shimamoto, S., Wicaksono, R. P., ... Chang, K. (2018). Novel UE RF condition estimation algorithm by integrating machine learning. In Mobile and Wireless Technologies 2017 - ICMWT 2017 (Vol. 425, pp. 102-113). (Lecture Notes in Electrical Engineering; Vol. 425). Springer Verlag. https://doi.org/10.1007/978-981-10-5281-1_12

Novel UE RF condition estimation algorithm by integrating machine learning. / Dong, Yupu; Pan, Zhenni; Ernawan, Mohamad Erick; Liu, Jiang; Shimamoto, Shigeru; Wicaksono, Ragil Putro; Kunishige, Seiji; Chang, Kwangrok.

Mobile and Wireless Technologies 2017 - ICMWT 2017. Vol. 425 Springer Verlag, 2018. p. 102-113 (Lecture Notes in Electrical Engineering; Vol. 425).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dong, Y, Pan, Z, Ernawan, ME, Liu, J, Shimamoto, S, Wicaksono, RP, Kunishige, S & Chang, K 2018, Novel UE RF condition estimation algorithm by integrating machine learning. in Mobile and Wireless Technologies 2017 - ICMWT 2017. vol. 425, Lecture Notes in Electrical Engineering, vol. 425, Springer Verlag, pp. 102-113, 4th iCatse Conference on Mobile and Wireless Technology, ICMWT 2017, Kuala Lumpur, Malaysia, 17/6/26. https://doi.org/10.1007/978-981-10-5281-1_12
Dong Y, Pan Z, Ernawan ME, Liu J, Shimamoto S, Wicaksono RP et al. Novel UE RF condition estimation algorithm by integrating machine learning. In Mobile and Wireless Technologies 2017 - ICMWT 2017. Vol. 425. Springer Verlag. 2018. p. 102-113. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-10-5281-1_12
Dong, Yupu ; Pan, Zhenni ; Ernawan, Mohamad Erick ; Liu, Jiang ; Shimamoto, Shigeru ; Wicaksono, Ragil Putro ; Kunishige, Seiji ; Chang, Kwangrok. / Novel UE RF condition estimation algorithm by integrating machine learning. Mobile and Wireless Technologies 2017 - ICMWT 2017. Vol. 425 Springer Verlag, 2018. pp. 102-113 (Lecture Notes in Electrical Engineering).
@inproceedings{125fb01538fd450daa032c1ef7b248f6,
title = "Novel UE RF condition estimation algorithm by integrating machine learning",
abstract = "By 2020, 5G era will be commercially available. The smart city construction will also make great progress. Compared to current situation, more than thousand times of devices will connect to the cellular networks. For the operators, in order to analyze overall network performance, it is a key factor to estimate the user equipment (UE) radio frequency (RF) condition. However, practical RF estimation scheme is based on UE data log which can only observe UE that is at the top-serving cell with good RF condition. However, according to the comparison of actual UE data log and the scanner data log, potential RF problems may still exist since the UE will not always be served by the top-1 cell. In this paper, we propose a novel estimation scheme by integrating machine learning (ML) algorithm to analyze the scanner data logs from the target estimation zones where the mobility problems may occur. A hypothesis is obtained from learning step by various kinds of RF condition as input features. The numerical results show that the proposed estimation algorithm integrated ML can estimate probability of the potential mobility problems accurately.",
keywords = "Estimation, Machine learning, Mobility problem, RF condition",
author = "Yupu Dong and Zhenni Pan and Ernawan, {Mohamad Erick} and Jiang Liu and Shigeru Shimamoto and Wicaksono, {Ragil Putro} and Seiji Kunishige and Kwangrok Chang",
year = "2018",
doi = "10.1007/978-981-10-5281-1_12",
language = "English",
isbn = "9789811052804",
volume = "425",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "102--113",
booktitle = "Mobile and Wireless Technologies 2017 - ICMWT 2017",
address = "Germany",

}

TY - GEN

T1 - Novel UE RF condition estimation algorithm by integrating machine learning

AU - Dong, Yupu

AU - Pan, Zhenni

AU - Ernawan, Mohamad Erick

AU - Liu, Jiang

AU - Shimamoto, Shigeru

AU - Wicaksono, Ragil Putro

AU - Kunishige, Seiji

AU - Chang, Kwangrok

PY - 2018

Y1 - 2018

N2 - By 2020, 5G era will be commercially available. The smart city construction will also make great progress. Compared to current situation, more than thousand times of devices will connect to the cellular networks. For the operators, in order to analyze overall network performance, it is a key factor to estimate the user equipment (UE) radio frequency (RF) condition. However, practical RF estimation scheme is based on UE data log which can only observe UE that is at the top-serving cell with good RF condition. However, according to the comparison of actual UE data log and the scanner data log, potential RF problems may still exist since the UE will not always be served by the top-1 cell. In this paper, we propose a novel estimation scheme by integrating machine learning (ML) algorithm to analyze the scanner data logs from the target estimation zones where the mobility problems may occur. A hypothesis is obtained from learning step by various kinds of RF condition as input features. The numerical results show that the proposed estimation algorithm integrated ML can estimate probability of the potential mobility problems accurately.

AB - By 2020, 5G era will be commercially available. The smart city construction will also make great progress. Compared to current situation, more than thousand times of devices will connect to the cellular networks. For the operators, in order to analyze overall network performance, it is a key factor to estimate the user equipment (UE) radio frequency (RF) condition. However, practical RF estimation scheme is based on UE data log which can only observe UE that is at the top-serving cell with good RF condition. However, according to the comparison of actual UE data log and the scanner data log, potential RF problems may still exist since the UE will not always be served by the top-1 cell. In this paper, we propose a novel estimation scheme by integrating machine learning (ML) algorithm to analyze the scanner data logs from the target estimation zones where the mobility problems may occur. A hypothesis is obtained from learning step by various kinds of RF condition as input features. The numerical results show that the proposed estimation algorithm integrated ML can estimate probability of the potential mobility problems accurately.

KW - Estimation

KW - Machine learning

KW - Mobility problem

KW - RF condition

UR - http://www.scopus.com/inward/record.url?scp=85022181162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022181162&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-5281-1_12

DO - 10.1007/978-981-10-5281-1_12

M3 - Conference contribution

SN - 9789811052804

VL - 425

T3 - Lecture Notes in Electrical Engineering

SP - 102

EP - 113

BT - Mobile and Wireless Technologies 2017 - ICMWT 2017

PB - Springer Verlag

ER -