TY - JOUR
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 outage UEs 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 articles use the common bias value among all UEs determined by trial-and-error method. In this article, 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 outage UEs 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 outage UEs 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 outage UEs 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 articles use the common bias value among all UEs determined by trial-and-error method. In this article, 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 outage UEs 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 outage UEs and improves network throughput.
UR - http://www.scopus.com/inward/record.url?scp=84878063165&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84878063165&partnerID=8YFLogxK
U2 - 10.1186/1687-1499-2013-61
DO - 10.1186/1687-1499-2013-61
M3 - Article
AN - SCOPUS:84878063165
VL - 2013
JO - Eurasip Journal on Wireless Communications and Networking
JF - Eurasip Journal on Wireless Communications and Networking
SN - 1687-1472
IS - 1
M1 - 61
ER -