Collaborative Social-Aware and QoE-Driven Video Caching and Adaptation in Edge Network

With the emerging demand for high-definition videos in recent years, Multi-access Edge Computing (MEC) has become a promising solution to leverage Quality of Experience (QoE) of users in the 5G mobile network, which provides computing and cache resource at network edges to serve end users with less latency. Also, since mobile users tend to be influenced by the trends in social media, the performance of video caching will become more effective if we can extract the hidden information from interaction among them. In this paper, we propose a novel Collaborative Social-aware QoE-driven video Caching and Adaption (CSQCA) framework. Specifically, we first design a 2-tier MEC collaborative video caching architecture, which partially caches popular videos among multiple edge servers. Second, we propose a social-aware proactive cache strategy, which embeds interactions of users and video dissemination process in social networks into the caching mechanism. Third, a QoE-driven video adaptation algorithm is presented to dynamically transcode the cached videos into appropriate resolution on edge server for each request. Finally, we conduct our simulation based on real-world datasets. The simulation results show that the proposed CSQCA framework outperforms traditional cache algorithms, in terms of the average hit ratio and QoE.