A Dynamic QoE Routing System for User-Centric Applications

International audienceToday, maintaining the best quality of experience (QoE) as the subjective perception of end-users is one of the most impor-tant requirements of both wireless and wired networks. To achieve this goal, we frequently use network functions suchas admission control, resource management, routing and traffic control. We focus on the design and evaluation of a QoE-aware routing mechanism. We present an end-to-end model where Smartphone users connect to content servers througha wired network across a wireless access network. We propose an adaptive and evolutionary system with a QoE-awarerouting protocol, namely QoE Q-learning-based adaptive routing. Our experimental results demonstrate significant perfor-mance improvements in mean opinion score for various network loads, convergence time during the initialisation phaseand control overheads over other traditional approaches