User QoE-based adaptive routing system for future Internet CDN

The most important tendency of future Internet architectures is maintaining the best Quality of Experience (QoE), which represents the subjective perception of end-users using network services with network functions such as admission control, resource management, routing, traffic control, etc. Among of them, we focus on routing mechanism driven by QoE end-users. Nowadays, most existing routing protocols have encountered NP-complete problem when trying to satisfy multi QoS constraints criteria simultaneously. With the intention for avoiding the classification problem of these multiple criteria reducing the complexity problem for the future Internet, we propose a protocol based on user QoE measurement in routing paradigm to construct an adaptive and evolutionary system. Our approach, namely QQAR (QoE Q-learning based Adaptive Routing), is based on Q-Learning, a Reinforcement Learning algorithm. QQAR uses Pseudo Subjective Quality Assessment (PSQA), a real-time QoE assessment tool based on Random Neural Network, to evaluate QoE. Experimental results showed a significant performance against over other traditional routing protocols.