Resumen de Data-Driven QoE Modeling for Real-Time Video Streaming and Web Browsing Services in Cellular Networks
In recent years, the number of users and services in mobile networks has increased significantly, rising user expectations, causing cellular networks to suffer significant changes to cope with the increasing demand for services. As a result, traffic in current mobile networks has increased exponentially due to data exchange from certain services, namely video and web browsing services. Video traffic generates the most significant volumes of data, increasing daily due to the emergence of new formats and innovative services, such as live streaming, 360◦ videos or virtual reality. On the other hand, web traffic generates the second-highest data volume because, in addition to the web browsing traffic, it is present to a greater or lesser degree in other types of services, such as video services (e.g., YouTube, Netflix, Amazon Prime video).
The increasing demand for network services with high-Quality Service (QoS) requirements sets new challenges for next-generation cellular networks, especially considering the high traffic volume generated and stored in the network by different services that converge on it. This trend has forced network operators to change how they manage their systems from a network-centric to a user-centric approach, mak- ing customer experience management a key process in the daily routine of network operators.
This thesis addresses the analysis and modeling of the user Quality of Experi- ence (QoE) of real-time video and web browsing services in cellular networks. For this purpose, the key factors affecting service performance are identified by leveraging information registered in connection traces with data mining techniques.
In the case of live video streaming, a parametric model is proposed to estimate the QoE of the encrypted YouTube Live service from packet-level data collected at the interfaces of a wireless network. Unlike previous works, the proposed method is valid for encrypted and adaptive video content.
The emergence of the 360◦ video service, with high bandwidth and low delay requirements, has made QoE modeling for live video streaming services more challenging. This work presents a study of the impact of the uplink of a mobile network on 360◦ live video streaming on YouTube. Unlike previous works, the analysis covers the ingest link, which strongly impacts the latency of live transmissions.
Regarding web browsing, an unsupervised web classification scheme is presented to group web pages according to content characteristics that affect the QoE perceived by the end-user. The analysis presented here shows that the properties of a web page strongly impact its loading process, including the download of its contents and its progressive rendering in the browser. Consequently, the content of the web page has a strong impact on the web browsing end-user experience.
The methods and analyses proposed in this thesis are based on real data collected in private wireless and cellular networks. The data comes from emulated interactions with the different services in a real environment. Therefore, the practical applicability of this thesis is a distinctive feature.
