TY - JOUR
T1 - Fairness resource allocation in blind wireless multimedia communications
AU - Zhou, Liang
AU - Chen, Min
AU - Qian, Yi
AU - Chen, Hsiao Hwa
PY - 2013
Y1 - 2013
N2 - Traditional α-fairness resource allocation in wireless multimedia communications assumes that the quality of experience (QoE) model (or utility function) of each user is available to the base station (BS), which may not be valid in many practical cases. In this paper, we consider a blind scenario where the BS has no knowledge of the underlying QoE model. Generally, this consideration raises two fundamental questions. Is it possible to set the fairness parameter α in a precisely mathematical manner? If so, is it possible to implement a specific α-fairness resource allocation scheme online? In this work, we will give positive answers to both questions. First, we characterize the tradeoff between the performance and fairness by providing an upper bound of the performance loss resulting from employing α-fairness scheme. Then, we decompose the α-fairness problem into two subproblems that describe the behaviors of the users and BS and design a bidding game for the reconciliation between the two subproblems. We demonstrate that, although all users behave selfishly, the equilibrium point of the game can realize the α-fairness efficiently, and the convergence time is reasonably short. Furthermore, we present numerical simulation results that confirm the validity of the analytical results.
AB - Traditional α-fairness resource allocation in wireless multimedia communications assumes that the quality of experience (QoE) model (or utility function) of each user is available to the base station (BS), which may not be valid in many practical cases. In this paper, we consider a blind scenario where the BS has no knowledge of the underlying QoE model. Generally, this consideration raises two fundamental questions. Is it possible to set the fairness parameter α in a precisely mathematical manner? If so, is it possible to implement a specific α-fairness resource allocation scheme online? In this work, we will give positive answers to both questions. First, we characterize the tradeoff between the performance and fairness by providing an upper bound of the performance loss resulting from employing α-fairness scheme. Then, we decompose the α-fairness problem into two subproblems that describe the behaviors of the users and BS and design a bidding game for the reconciliation between the two subproblems. We demonstrate that, although all users behave selfishly, the equilibrium point of the game can realize the α-fairness efficiently, and the convergence time is reasonably short. Furthermore, we present numerical simulation results that confirm the validity of the analytical results.
UR - http://www.scopus.com/inward/record.url?scp=84877905150&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84877905150&partnerID=8YFLogxK
U2 - 10.1109/TMM.2013.2237895
DO - 10.1109/TMM.2013.2237895
M3 - Article
AN - SCOPUS:84877905150
SN - 1520-9210
VL - 15
SP - 946
EP - 956
JO - IEEE Transactions on Multimedia
JF - IEEE Transactions on Multimedia
IS - 4
M1 - 6403550
ER -