Cell range expansion using distributed Q-learning in heterogeneous networks

Toshihito Kudo, Tomoaki Ohtsuki

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

11 Citations (Scopus)

Abstract

Cell range expansion (CRE) is a technique to expand a pico cell range virtually by adding a bias value to the pico received power, instead of increasing transmit power of pico base station (PBS), so that coverage, cell-edge throughput, and overall network throughput are improved. Many studies have focused on inter-cell interference coordination (ICIC) in CRE, because macro base station's (MBS's) strong transmit power harms the expanded region (ER) user equipments (UEs) that select PBSs by bias value. Optimal bias value that minimizes the number of UE outages depends on several factors such as the dividing ratio of radio resources between MBSs and PBSs. In addition it varies from UE to another. Thus, most papers use the common bias value among all UEs determined by a trial and error method. In this paper we propose a scheme to determine the bias value of each UE by using Q-learning algorithm where each UE learns its bias value that minimizes the number of UE outages from its past experience independently. Simulation results show that, compared to the scheme using optimal common bias value, the proposed scheme reduces the number of UE outages and improves network throughput.

Original languageEnglish
Title of host publicationIEEE Vehicular Technology Conference
DOIs
Publication statusPublished - 2013
Event2013 IEEE 78th Vehicular Technology Conference, VTC Fall 2013 - Las Vegas, NV, United States
Duration: 2013 Sep 22013 Sep 5

Other

Other2013 IEEE 78th Vehicular Technology Conference, VTC Fall 2013
CountryUnited States
CityLas Vegas, NV
Period13/9/213/9/5

Fingerprint

Q-learning
Heterogeneous networks
Heterogeneous Networks
Cell
Range of data
Outages
Throughput
Base stations
Minimise
Trial and error
Learning algorithms
Expand
Macros
Learning Algorithm
Coverage
Interference
Vary
Resources

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Applied Mathematics

Cite this

Cell range expansion using distributed Q-learning in heterogeneous networks. / Kudo, Toshihito; Ohtsuki, Tomoaki.

IEEE Vehicular Technology Conference. 2013. 6692125.

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

Kudo, T & Ohtsuki, T 2013, Cell range expansion using distributed Q-learning in heterogeneous networks. in IEEE Vehicular Technology Conference., 6692125, 2013 IEEE 78th Vehicular Technology Conference, VTC Fall 2013, Las Vegas, NV, United States, 13/9/2. https://doi.org/10.1109/VTCFall.2013.6692125
Kudo, Toshihito ; Ohtsuki, Tomoaki. / Cell range expansion using distributed Q-learning in heterogeneous networks. IEEE Vehicular Technology Conference. 2013.
@inproceedings{efde8bfad925417594ad6987fff3b156,
title = "Cell range expansion using distributed Q-learning in heterogeneous networks",
abstract = "Cell range expansion (CRE) is a technique to expand a pico cell range virtually by adding a bias value to the pico received power, instead of increasing transmit power of pico base station (PBS), so that coverage, cell-edge throughput, and overall network throughput are improved. Many studies have focused on inter-cell interference coordination (ICIC) in CRE, because macro base station's (MBS's) strong transmit power harms the expanded region (ER) user equipments (UEs) that select PBSs by bias value. Optimal bias value that minimizes the number of UE outages depends on several factors such as the dividing ratio of radio resources between MBSs and PBSs. In addition it varies from UE to another. Thus, most papers use the common bias value among all UEs determined by a trial and error method. In this paper we propose a scheme to determine the bias value of each UE by using Q-learning algorithm where each UE learns its bias value that minimizes the number of UE outages from its past experience independently. Simulation results show that, compared to the scheme using optimal common bias value, the proposed scheme reduces the number of UE outages and improves network throughput.",
author = "Toshihito Kudo and Tomoaki Ohtsuki",
year = "2013",
doi = "10.1109/VTCFall.2013.6692125",
language = "English",
isbn = "9781467361873",
booktitle = "IEEE Vehicular Technology Conference",

}

TY - GEN

T1 - Cell range expansion using distributed Q-learning in heterogeneous networks

AU - Kudo, Toshihito

AU - Ohtsuki, Tomoaki

PY - 2013

Y1 - 2013

N2 - Cell range expansion (CRE) is a technique to expand a pico cell range virtually by adding a bias value to the pico received power, instead of increasing transmit power of pico base station (PBS), so that coverage, cell-edge throughput, and overall network throughput are improved. Many studies have focused on inter-cell interference coordination (ICIC) in CRE, because macro base station's (MBS's) strong transmit power harms the expanded region (ER) user equipments (UEs) that select PBSs by bias value. Optimal bias value that minimizes the number of UE outages depends on several factors such as the dividing ratio of radio resources between MBSs and PBSs. In addition it varies from UE to another. Thus, most papers use the common bias value among all UEs determined by a trial and error method. In this paper we propose a scheme to determine the bias value of each UE by using Q-learning algorithm where each UE learns its bias value that minimizes the number of UE outages from its past experience independently. Simulation results show that, compared to the scheme using optimal common bias value, the proposed scheme reduces the number of UE outages and improves network throughput.

AB - Cell range expansion (CRE) is a technique to expand a pico cell range virtually by adding a bias value to the pico received power, instead of increasing transmit power of pico base station (PBS), so that coverage, cell-edge throughput, and overall network throughput are improved. Many studies have focused on inter-cell interference coordination (ICIC) in CRE, because macro base station's (MBS's) strong transmit power harms the expanded region (ER) user equipments (UEs) that select PBSs by bias value. Optimal bias value that minimizes the number of UE outages depends on several factors such as the dividing ratio of radio resources between MBSs and PBSs. In addition it varies from UE to another. Thus, most papers use the common bias value among all UEs determined by a trial and error method. In this paper we propose a scheme to determine the bias value of each UE by using Q-learning algorithm where each UE learns its bias value that minimizes the number of UE outages from its past experience independently. Simulation results show that, compared to the scheme using optimal common bias value, the proposed scheme reduces the number of UE outages and improves network throughput.

UR - http://www.scopus.com/inward/record.url?scp=84893325343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893325343&partnerID=8YFLogxK

U2 - 10.1109/VTCFall.2013.6692125

DO - 10.1109/VTCFall.2013.6692125

M3 - Conference contribution

AN - SCOPUS:84893325343

SN - 9781467361873

BT - IEEE Vehicular Technology Conference

ER -