|Authors||K. Evensen, D. Kaspar, C. Griwodz, P. Halvorsen, A. F. Hansen and P. E. Engelstad|
|Title||Using Bandwidth Aggregation to Improve the Performance of Quality-Adaptive Streaming|
|Afilliation||Communication Systems, , Communication Systems|
|Publication Type||Journal Article|
|Year of Publication||2011|
|Journal||Signal Processing: Image Communication|
Devices capable of connecting to multiple, overlapping networks simultaneously is becoming increasingly common. For example, most laptops are equipped with LAN- and WLAN-interface, and smart phones can typically connect to both WLANs and 3G mobile networks. At the same time, streaming high-quality video is becoming increasingly popular. However, due to bandwidth limitations or the unreliable and unpredictable nature of some types of networks, streaming video can be subject to frequent periods of rebuffering and characterized by a low picture quality. In this paper, we present a multilink extension to the data retrieval part of the DAVVI adaptive, segmented video streaming system. DAVVI implements the same core functionality as the MPEG DASH standard. It uses HTTP to retrieve data, segments video, provides clients with a description of the content, and allows clients to switch quality during playback. Any DAVVI-data retrieval extensions can also be implemented in a DASH-solution. The multilink-enabled DAVVI client divides video segments into smaller subsegments, which are requested over multiple interfaces simultaneously. The size of each subsegment is dynamic and calculated on the fly, based on the throughput of the different links. This is an improvement over our earlier subsegment approach, which divided segments into fixed size subsegments. The quality of the video is adapted based on the measured, aggregated throughput. Both the static and the dynamic subsegment approaches were evaluated with on-demand streaming and quasi-live streaming. The new subsegment approach reduces the number of playback interruptions and improves video quality significantly for all cases where the earlier approach struggled. Otherwise, they show similar performance.