QoE-Driven Integrated Heterogeneous Traffic Resource Allocation Based on Cooperative Learning for 5G Cognitive Radio Networks

Abstract

Since quality measurement of end user plays an ever increasing role in development of the wireless communications toward the 5G era, mean opinion score (MOS) has become a widely used metric, not only because it reflects the subjective quality experience of end users but it also provides a common quality assessment metric for traffic of different types. This paper presents a distributed underlay dynamic spectrum access (DSA) scheme based on MOS which performs integrated traffic management and resource allocation across traffics of dissimilar characteristics (real-time video and data traffic). The presented scheme maximizes the overall MOS through a reinforcement learning for a system where primary users coexist with secondary users accessing the same frequency band of interest, while satisfying a total interference constraint to the primary users. The use of MOS as a common metric allows teaching between nodes carrying different traffic without reducing performance. As a result, the docitive paradigm is applied to the presented scheme to investigate the impact of different docition scenarios on overall MOS where a new comer node being taught by experienced peers with similar and dissimilar traffics. Simulation results show that the docition will reduce the number of iterations required for convergence by approximately 65% while preserving the overall MOS more than acceptable level (MOS >3) for different secondary network loads. In terms of applying docition between nodes with similar and dissimilar traffic, simulation results show all different docition scenarios have the same performance in terms of MOS.