Dependency- and similarity-aware caching for HTTP adaptive streaming

There has been significant interest in the use of HTTP adaptive streaming for live or on-demand video over the Internet in recent years. To mitigate the streaming transmission delay and reduce the networking overhead, an effective and critical approach is to utilize cache services between the origin servers and the heterogeneous clients. As the underlying protocol for web transactions, HTTP has great potentials to explore the resources within state-of-the-art CDNs for caching; yet distinct challenges arise in the HTTP adaptive streaming context. After examining a long-term and large-scale adaptive streaming dataset as well as statistical analysis, we demonstrate that the switching requests among the different qualities frequently emerge and constitute a significant portion in a per-day view. Consequently, they have substantially affected the performance of cache servers and Quality-of-Experience (QoE) of viewers. In this paper, we propose a novel cache model that captures the dependency among the segments in the cache server for adaptive HTTP streaming. Our work does not assume any specific selection algorithm on the client's side and hence can be easily incorporated into existing streaming cache systems. Its centralized nature is also well accommodated by the latest DASH specification. Moreover, we extend our work to the multi-server caching context and present a similarity-aware allocation mechanism to enhance the caching efficiency. The performance evaluation shows our dependency- and similarity-aware strategy can significantly improve the cache hit-ratio and QoE of HTTP streaming as compared to previous approaches.