“…This is not only wasteful in both network and base-station resources but also increases the user-perceived playout latency. Therefore, we resort to using video segmentation [14], [21] in order to reduce network transmission costs between the video-holding media server and its subordinates base-stations. Segmentation also decreases the start-up latency that users experience upon cell entrance.…”
The emergence of third-generation (3G) mobile networks offers new opportunities for the effective delivery of data with rich content including multimedia messaging and video-streaming. Provided that streaming services have proved highly successful over stationary networks in the past, we anticipate that the same trend will soon take place in 3G networks. Although mobile operators currently make available pertinent services, the available resources of the underlying networks for the delivery of rich data remain inherently constrained. At this stage and in light of large numbers of users moving fast across cells, 3G networks may not be able to warrant the needed quality-of-service requirements. The support for streaming services necessitates the presence of content or media servers properly placed over the 3G network; such servers essentially become the source for streaming applications. Evidently, a centralized approach in organizing streaming content might lead to highly congested media-nodes which in presence of moving users will certainly yield increased response times and jitter to user requests. In this paper, we propose a workaround that enables 3G networks to offer uninterrupted video-streaming services in the presence of a large number of users moving in high-speed. At the same time, we offer a distributed organization for the network's mediaservers to better handle over-utilization.
“…This is not only wasteful in both network and base-station resources but also increases the user-perceived playout latency. Therefore, we resort to using video segmentation [14], [21] in order to reduce network transmission costs between the video-holding media server and its subordinates base-stations. Segmentation also decreases the start-up latency that users experience upon cell entrance.…”
The emergence of third-generation (3G) mobile networks offers new opportunities for the effective delivery of data with rich content including multimedia messaging and video-streaming. Provided that streaming services have proved highly successful over stationary networks in the past, we anticipate that the same trend will soon take place in 3G networks. Although mobile operators currently make available pertinent services, the available resources of the underlying networks for the delivery of rich data remain inherently constrained. At this stage and in light of large numbers of users moving fast across cells, 3G networks may not be able to warrant the needed quality-of-service requirements. The support for streaming services necessitates the presence of content or media servers properly placed over the 3G network; such servers essentially become the source for streaming applications. Evidently, a centralized approach in organizing streaming content might lead to highly congested media-nodes which in presence of moving users will certainly yield increased response times and jitter to user requests. In this paper, we propose a workaround that enables 3G networks to offer uninterrupted video-streaming services in the presence of a large number of users moving in high-speed. At the same time, we offer a distributed organization for the network's mediaservers to better handle over-utilization.
“…Client requests arrive according to a Poisson process [10] [17]. All clients are always redirected to the closest server without failure of request routing.…”
“…Some other researchers have considered the disk model, such as the RAID [21] disk model, and multicast [20] for client interactive request support. On the proxy side, some solutions to support client interactive requests for Internet streaming delivery have also been proposed to create additional data files, called summarization [16] or hotspots [9], containing discontinuous but representative scenes of a media object, and cache them separately from the media files. In [16], the proxy is responsible for shot boundary detection and key-frame selection and summarization.…”
Section: Related Workmentioning
confidence: 99%
“…On the proxy side, some solutions to support client interactive requests for Internet streaming delivery have also been proposed to create additional data files, called summarization [16] or hotspots [9], containing discontinuous but representative scenes of a media object, and cache them separately from the media files. In [16], the proxy is responsible for shot boundary detection and key-frame selection and summarization. A client can preview the summarization to decide whether he/she is going to continue the request.…”
Section: Related Workmentioning
confidence: 99%
“…They usually require the creation of additional data files in the proxy or in the media server and can support only a limited set of interactive operations such as fast forward, rewind, and preview [9,16]. None of them provides effective support for jumps, which according to a recent study are among the dominant interactive operations from clients [6].…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.