TY - JOUR
T1 - Traffic-aware online network selection in heterogeneous wireless networks
AU - Wu, Qihui
AU - Du, Zhiyong
AU - Yang, Panlong
AU - Yao, Yu Dong
AU - Wang, Jinlong
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - We focus on the network selection problem in heterogeneous wireless networks. Many traditional approaches select the best network according to quality of service (QoS)-related criteria, which neglects diverse user demands. We aim to select networks maximizing the quality of experience (QoE) of users. When the availability and dynamics of network state information (NSI) are considered, most of the existing approaches cannot make effective selection decisions since they are vulnerable to the uncertainty in NSI. To address this issue, we introduce the idea of online learning for network selection. In this paper, we formulate the network selection problem as a continuous-time multiarmed bandit (CT-MAB) problem. A traffic-aware online network selection (ONES) algorithm is designed to match typical traffic types of users with respective optimal networks in terms of QoE. Moreover, we found that the correlation among multiple traffic network selections can be exploited to improve the learning capability. This motivates us to propose another two more efficient algorithms: the decoupled ONES (D-ONES) algorithm and the virtual multiplexing ONES (VM-ONES) algorithm. Simulation results demonstrate that our ONES algorithms attain around 10% gain in QoE reward rate over nonlearning-based algorithms and learning-based algorithms without QoE considerations.
AB - We focus on the network selection problem in heterogeneous wireless networks. Many traditional approaches select the best network according to quality of service (QoS)-related criteria, which neglects diverse user demands. We aim to select networks maximizing the quality of experience (QoE) of users. When the availability and dynamics of network state information (NSI) are considered, most of the existing approaches cannot make effective selection decisions since they are vulnerable to the uncertainty in NSI. To address this issue, we introduce the idea of online learning for network selection. In this paper, we formulate the network selection problem as a continuous-time multiarmed bandit (CT-MAB) problem. A traffic-aware online network selection (ONES) algorithm is designed to match typical traffic types of users with respective optimal networks in terms of QoE. Moreover, we found that the correlation among multiple traffic network selections can be exploited to improve the learning capability. This motivates us to propose another two more efficient algorithms: the decoupled ONES (D-ONES) algorithm and the virtual multiplexing ONES (VM-ONES) algorithm. Simulation results demonstrate that our ONES algorithms attain around 10% gain in QoE reward rate over nonlearning-based algorithms and learning-based algorithms without QoE considerations.
KW - Online learning
KW - Online network selection (ONES)
KW - Quality of experience (QoE)
KW - Terms-Heterogeneous wireless networks
KW - Traffic type
UR - http://www.scopus.com/inward/record.url?scp=84959351577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959351577&partnerID=8YFLogxK
U2 - 10.1109/TVT.2015.2394431
DO - 10.1109/TVT.2015.2394431
M3 - Article
AN - SCOPUS:84959351577
SN - 0018-9545
VL - 65
SP - 381
EP - 397
JO - IEEE Transactions on Vehicular Technology
JF - IEEE Transactions on Vehicular Technology
IS - 1
M1 - 7018008
ER -