The rapid growth of video traffic in cellular networks is a crucial issue to be addressed by mobile operators. An emerging and promising trend in this regard is the development of solutions that aim at maximizing the Quality of Experience (QoE) of the end users. However, predicting the QoE perceived by the users in different conditions remains a major challenge. In this paper, we propose a machine learning approach to support QoE-based Video Admission Control (VAC) and Resource Management (RM) algorithms. More specifically, we develop a learning system that can automatically extract the quality-rate characteristics of unknown video sequences from the size of H.264-encoded video frames. Our approach combines unsupervised feature learning with supervised classification techniques, thereby providing an efficient and scalable way to estimate the QoE parameters that characterize each video. This QoE characterization is then used to manage simultaneous video transmissions through a shared channel in order to guarantee a minimum quality level to the final users. Simulation results show that the proposed learning-based QoE classification of video sequences outperforms commonly deployed off-line video analysis techniques and that the QoE-based VAC and RM algorithms outperform standard content-agnostic strategies

The exponential growth of video traffic in mobile networks calls for the deployment of advanced video admission control (VAC) and resource management (RM) techniques in order to provide the best quality of experience (QoE) to the end user according to the available network resources. The degradation of the QoE perceived by the user when reducing the source rate of a video typically depends on the content of the video itself. In this paper, we analyzed the QoE of a group of test video sequences encoded with H.264 advanced video codec at different rates, i.e., quality levels. The QoE is objectively expressed in terms of the average structural similarity (SSIM) index. Based on empirical results, we propose a 4-degree polynomial approximation of the SSIM as a function of the coded video rate. We hence propose to tag each video with these polynomial coefficients that provide a compact description of its specific SSIM behavior, and to use this information in VAC and RM algorithms to optimally manage a shared transmission medium. As a proof of concept, we report selected simulation results that compare QoE-aware and QoE-agnostic algorithms in a scenario with a single link shared by multiple concurrent video flows

No abstract

Video mobile applications can be served via multiple delivery paths from the video server to the end user, thus delivering different video qualities. Throughput and delay highly depend on the video paths available in the core network and on the availability of wireless access technologies in the last hop. We consider a set of characteristics of the whole video delivery chain to univocally identify each available path and we develop a framework for the selection of the best video path in terms of throughput and packet delivery delay. We further extend the framework, implementing at the access points a tunable traffic shaping mechanism to decrease the delivery delay while maintaining the number of packets delivered. We evaluate our framework by means of simulation in ns-3, an event-based network simulator able to accurately model the Long Term Evolution (LTE) core and access networks