Adaptive, best-effort delivery of digital audio and video across packet-switched networks

Abstract

We present an overview of a “best-effort” transport protocol that supports conferencing with digital audio and video across interconnected packet switched networks. The protocol delivers the highest quality conference service possible given the current load in the network. Quality is defined in terms of synchronization between audio and video, the number of frames played out of order, and the end-to-end latency in the conference. High quality conferences are realized through four transport and display mechanisms and a real-time implementation of these mechanisms that integrates operating system services (e.g., scheduling and resource allocation, and device management) with network communication services (e.g., transport protocols). In concert these mechanisms dynamically adapt the conference frame rate to the bandwidth available in the network, minimize the latency in the displayed streams while avoiding discontinuities, and provide quasi-reliable delivery of audio frames.

This work supported by the National Science Foundation (grant numbers CCR-9110938 and ICI-9015443), and by the Digital Equipment Corporation and the IBM Corporation.