Workshop on Ultra-Large Networks: Challenges and New Research Directions for Modeling and Simulation

我们建议2001年秋季在亚利桑那州图森市举办一个为期两天的研讨会，主题是新兴的超大型网络，如互联网。会议由亚利桑那州综合建模与仿真中心主办，会议将汇集网络领域的一些世界领先的研究人员，与在网络和更广泛的系统的建模和仿真方面具有专业知识的同行会面。研讨会将为这些研究人员提供提出超大型网络的未知数的任务，并为能够解决这些未知数的建模和模拟提供新的研究方向。互联网的连通性正在增加，2005年接近10亿个节点，节点能力提供了高度互联和计算能力强大的媒介。这样一个全球和无处不在的分散的网络将为新型的教育、商业和娱乐活动提供一个新的前沿。然而，在出现这样一个巨大的、高度分散的、互动部分的集合时，会出现许多问题。增加的连接性和能力创造了新的复杂性和动态，我们即将欣赏到这些。处理大型软件系统的困难在国家研究委员会最近的一份报告中得到了很好的记录。当规模扩大一百万倍时，适用于小型软件系统的技术就会明显失败。需要基于计算机的建模和仿真(M&S)方法来解决这些问题，因为规模远远超出了仅靠分析工具所能处理的范围，而且在Always On Internet上进行受控实验的能力有限。传统的并购S方法侧重于微观层面的组件，而不是这些组件的宏观集成。然而，随着未来互联网等超大规模系统的到来，有必要开发M&Amp；S方法来理解非常大的互联网络的行为，这些网络几乎没有控制点，有许多相互作用的和不同的输入和服务需求来源。预计此次研讨会的结果将是我们在了解超大型网络的行为以及如何处理其设计、管理和控制方面的一系列具体发现。参与者可能会评估当前的方法是否可以演变成应对规模的大幅增长，或者是否需要不同的革命性范式。与会者将讨论建立超大型网络模型和开发模拟环境以研究其行为的新技术和方法的需求。将鼓励借鉴其他领域的观点，如复杂适应系统和建模和仿真的基本理论。这些程序将以一种形式编制，将为未来网络基础设施研究的新的NSF资金倡议提供一个有用和重要的指南。

We propose to hold a two-day workshop in Tucson, Arizona during fall 2001 on emerging ultra-largenetworks, such as the Internet. Hosted by Arizona Center for Integrative Modeling and Simulation, themeeting will bring together some of the world's leading researchers in the networking area to meet withcounterparts with expertise in modeling and simulation of networks and of systems more generally. Theworkshop will provide these researchers with the task of coming up with the unknowns of ultra-largenetworks and with new directions of research in modeling and simulation that can address these unknowns. The Internet is increasing in connectivity, toward 1 billion nodes in 2005 and node capability providing ahighly interconnected and computationally powerful medium. Such a globally and ubiquitously dispersednetwork will provide a new frontier for new kinds of educational, commerce and entertainment activities.However, there are many issues that arise in the emergence of such a large, highly decentralized, collectionof interaction parts. The increased connectivity and capability creates new complexity and dynamics thatwe are only on the verge of appreciating. Difficulties in dealing with large-scale software systems are welldocumented in a recent report by the National Research Council. Techniques that work for small softwaresystems fail markedly when the scale is increased by one million fold. Computer-based modeling andsimulation (M&S) methodology is required to address these issues since the scale is well beyond whatanalytical tools alone can handle and there is limited ability to do controlled experiments on the alwayson Internet. Traditional M&S approaches have focussed on the micro-level components rather than themacro level integration of these components. However, with the advent of ultra-large scale systems such asthe Internet of the future, it is necessary to develop M&S approaches for understanding the behaviors ofvery large inter-connected networks with very few loci of control and many interacting and varied sourcesof input and services demand. The results of this workshop are expected to be a set of specific finding of gaps in our knowledge of thebehavior of ultra-large networks and how to deal with their design, management, and control. Participantsmay assess whether current approaches can be evolved to deal with the large increases in scale or whetherdifferent, revolutionary paradigms are required. Participants will address the need for new techniques andapproaches for building models of ultra-large networks and developing simulation environments forstudying their behaviors. Suggestions for borrowing points of view form other areas such as complexadaptive systems and from basic theory of modeling and simulation will be encouraged. The proceedingswill be compiled in a form that will provide a useable and significant guide for new NSF funding initiativesfor future network infrastructure research.