Cloud-assisted buffer management for HTTP-based mobile video streaming

This paper studies a cloud-assisted procedure to improve the user's Quality of Experience (QoE) in HTTP Adaptive Streaming (HAS) services. HAS delivers video streaming services following a client-server architecture and requires the client to originate repeated HTTP requests to download chunks of encoded video. In state-of-the-art systems, the client selects the actual chunk to be downloaded from a finite set of differently encoded video versions available at the server site, according to a client-based buffer management procedure. In a multimedia cloud framework, HAS can leverage knowledge of the characteristics of the encoded video available at the server side. Therefore, we propose a cloud-assisted HAS procedure that exploits information on the encoded video content available at the cloud side to control the client-originated download requests. The proposed approach balances client-related quality issues, which would require intensive video chunks download to avoid playout stalls, with cloud related system constraints, which require the average download rate not to overcome the average video encoding rate. Finally, this approach procedure alleviates the computational load at the client, since the downloading strategy is computed at the cloud side. We demonstrate that significant QoE improvements are achievable through the proposed cloud-assisted buffer management procedure. © 2013 ACM.