Analysis, modeling and generation of self-similar VBR video traffic
SIGCOMM '94 Proceedings of the conference on Communications architectures, protocols and applications
Traffic descriptors for VBR video teleconferencing over ATM networks
IEEE/ACM Transactions on Networking (TON)
Fundamental limits and tradeoffs of providing deterministic guarantees to VBR video traffic
Proceedings of the 1995 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Efficient network QoS provisioning based on per node traffic shaping
IEEE/ACM Transactions on Networking (TON)
Network Bandwidth Allocation and Admission Control for a Continuous Media File Server
IDMS '99 Proceedings of the 6th International Workshop on Interactive Distributed Multimedia Systems and Telecommunication Services
A node-to-node communication architecture for congestion avoidance of live video over the internet
ICCC '02 Proceedings of the 15th international conference on Computer communication
Interactive video on demand over high speed networks
Journal of High Speed Networks
Interactive video over ATM: state of the art
Computer Communications
Hi-index | 0.00 |
Transmission of variable-bitrate (VBR) video over ATM is a challenge because it combines the requirement for on-time data delivery with a bursty traffic characteristic. We focus on the role of ATM endsystems in the transmission of VBR video and examine how traffic shaping in the sender reduces the burstiness of the video stream and therefore the network resource requirements, both for video encoded in real-time and stored video. Shapers based on multiple leaky buckets are popular because they are particularly simple to implement. We present basic results on their buffer requirements and provide new, tighter bounds for their output traffic, enabling efficient resource allocation as well as a significant reduction in the number of leaky buckets required. We extend the basic shaping mechanism to provide efficient shaping for stored video. Finally we compare empirically the performance of multiple leaky bucket shaping with an optimal algorithm for MPEG-1 encoded video and find under realistic conditions near-optimal performance with very few leaky buckets.