Exploiting User Demand Diversity in Heterogeneous Wireless Networks

Abstract

Radio resource management (RRM) is crucial for improving resource utilization in heterogeneous wireless networks. Existing work attempts to exploit the network diversity to gain throughput improvement for users, which, however, neglects the impact of user demand on RRM. Armed with the idea that the ultimate goal of communications is to serve users with personalized demand, we introduce another dimension of potential performance gain, user demand diversity gain. This gain derives from the elaborate matching between user demand and radio resource, which can not be directly attained in existing throughput-centric optimization due to users' blindness in maximizing throughput. Aiming at obtaining this gain, we propose the user demand-centric optimization, where users seek to maximize quality of experience (QoE), instead of throughput. This shift enables us to propose a novel game formulation, QoE game. We derive the condition on the existence of the QoE equilibrium, validate the user demand diversity gain and propose a distributed QoE equilibrium learning algorithm. Finally, a cloud assisted learning framework is proposed to accommodate the learning algorithm with significantly reduced cost. Simulation results validate the existence of user demand diversity gain and the effectiveness of the proposed learning algorithm in improving the system efficiency and QoE fairness.Index Terms-Heterogeneous wireless network, radio resource management, user demand diversity, QoE game.

Spectrum Access and Power Control for Cognitive Satellite Communications: A Game-Theoretical Learning Approach

“…No-regret learning [33] and stochasticlearning automata [31] converge to the local optimum. To satisfy the above two requirement simultaneously, we resort to trial and error learning algorithm [36], [37], which is fully distributed and statistically converges to the best NE (efficient NE). However, to satisfy the convergence conditions of the algorithm, it is necessary to design the coefficients based on the value of the utility function that are measured multiple times.…”

“…In the algorithm, G(x) and F(x) are strictly decreasing functions, which denote the probability of accepting the outcome of an experiment. According to [36], [37], they have the general forms:…”

Context-aware and priority-based user association and resource allocation in heterogeneous wireless networks

“…The studies [14] and [15] have explored the problem of optimizing the user-centric satisfaction while considering userdemand diversity. However, their proposed optimization function and system model do not follow the specific-accesstechnology constraints.…”

“…Instead, a generalized problem formulation is proposed. Furthermore, the optimization problem in [14] do not consider the user preferences.…”

Reinforcement Learning Based Network Selection for Hybrid VLC and RF Systems

“…This vision is important since many newly emerging traffic types such as virtual reality need customized performance requirements. Although there is extensive research on network selection, e.g., [2][3], the utility design differentiating uplink and downlink requirements of different traffic types proposed in this paper seems to be absent. Second, the idea of transfer learning [4] based algorithm is used in network selection.…”