SCHEDULING AND BANDWIDTH ALLOCATION FOR THE DISTRIBUTION OF ARCHIVED VIDEO IN VOD SYSTEMS

Providing cost-effective video-on-demand (VOD) services necessitates r educing the required bandwidth for transporting video over high-speed networks. In this paper, we investigate efficient schemes for transpor ting archived MPEG-coded video over a VOD distribution network. A vide o stream is characterized by a time-varying traffic envelope, which pr ovides an upper bound on the bit rate. Using such envelopes, we show t hat video streams can be scheduled for transmission over the network s uch that the per-stream allocated bandwidth is significantly less than the source peak rate. In a previous work [13], we investigated stream scheduling and bandwidth allocation using global traffic envelopes an d homogeneous streams. In this paper, we generalize the scheduling sch eme in [13] to include the heterogeneous case. We then investigate the allocation problem under window-based traffic envelopes, which provid e tight bounds on the bit rate. Using such envelopes, we introduce thr ee stream-scheduling schemes for multiplexing video connections at a s erver. The performance of these schemes is evaluated under static and dynamic scenarios. Our results indicate a significant reduction in the per-stream allocated bandwidth when stream scheduling is used. While this reduction is obtained through statistical multiplexing, the trans ported streams are guaranteed stringent, deterministic quality of serv ice (i.e., zero loss rate and small, bounded delay). In contrast to vi deo smoothing, our approach requires virtually no buffer at the set-to p box since frames are delivered at their playback rate.