Real-Time Traffic Transmission Over the Internet TITLE2:

Multimedia applications require the transmission of real-time streams over a network. These streams often exhibit variable bandwidth requirements, and require high bandwidth and guarantees from the network. This creates problems when such streams are delivered over the Internet. To solve these problems, recently, a small set of differentiated services has been introduced. Among these, Premium Service can provide low loss and low end-end delay to a real-time stream. It uses a bandwidth allocation mechanism (BAM) based on the traffic peak rate. Since the bandwidth requirement of a video stream can be quite variable, this can result in a high cost to the user and a inefficient use of network bandwidth. In this paper we consider stored video streams and introduce a BAM that can increase bandwidth utilization and decrease the allocated bandwidth without affecting the QoS of the delivered real-time stream and without introducing any modification in the Premium Service. Although the proposed BAM can substantially reduce bandwidth consumption, we introduce several frame dropping mechanisms that further reduce bandwidth consumption subject to a QoS constraint when coupled with the above BAM. The proposed BAM and the heuristics algorithms are evaluated using Motion JPEG and MPEG videos and are shown to be effective in reducing bandwidth requirements.