Proxy Services in Wide Area Networks

点击翻译按钮获取中文摘要

Interest in streaming media services has grown dramatically in recent years due to the unparalleled popularity of the Internet and the increase in backbone and access bandwidth. As client access bandwidth further increases, the demand for high-quality audio/video streaming will grow. Emerging applications include orchestrated media applications, such as distance learning, that combine audio, video, images, and text from one or more sources. Other challenging multimedia applications are on the horizon, including virtual reality and distributed interactive simulation. These applications involve both constant-bit-rate and variable-bit-rate streams of varying popularity, and different degrees of support for user interactivity, such as VCR or branching operations. These emerging high-quality multimedia applications will pose serious challenges to the network infras-tructure. A common thread among these applications is the so-called "continuous" nature of their data. In continuous media (CM), strict timing relationships exist that define the schedule by which CM data must be rendered (e.g., a video displayed or audio played out). In a network setting, the playout timing constraints, the rate variability of specific CM such as variable bit rate (VBR) video, the possibility of packet loss and delay within the network, and the desire to use network resources efficiently combine to make the delivery of CM data an exceptionally challenging problem. The challenge of delivering high-quality audio and video is further complicated by the fact that a single network service provider typically does not control the entire path from the source to the end client(s). One promising approach to addressing these challenges is to deploy proxy services within the network. Proxies can hide heterogeneity, reduce user start-up latency, lower the network resource usage, and adapt to fluctuations in network performance properties. In this proposal, the project director outlines research whose goal is to develop and evaluate proxy services that improves the perceived quality of CM streams seen by clients while providing low startup latencies. The project will focus on the development of the services themselves, the underlying resource management mechanisms required at the proxy, the programming interface required so that these services access the resource management mechanisms, and characterizations of the workloads and access patterns typically encountered by such proxies. The approach to evaluating these services and mechanisms is eclectic, relying on a combination of analysis, simulation, and experimentation with a Linux-based proxy, PRONTO, which will be further enhanced throughout the project.