PARTAGE: An Open Peer-to-Peer Infrastructure for Cycle-Sharing

Hu/Vitek摘要复杂和大型科学应用的大规模计算周期共享是分布式计算中的一个长期挑战。已经开发了许多循环共享系统，并在可用资源方面提供了数量级的改进。然而，它们的性能或能力有限。此外，为了实现真正分布式的科学基础设施，还需要其他形式的资源共享和协调。该项目的目标是通过开发向研究人员开放的虚拟实验室的使能技术，为国家科学和技术基础设施做出贡献所有学科。这个基础设施将利用对等计算和编程语言的资源，为广域网上的资源共享提供一个替代的架构模型。对等网络的自组织特性有望消除配置和维护大规模全球分布式计算和控制系统所需的许多困难，而分散化消除了集中服务节点的潜在瓶颈和单点故障。 该项目的贡献将是提供基于扩展面向对象编程模型的对等计算的抽象，并开发一个对等基础设施，该基础设施扩展了当前为路由和数据中心应用开发的对等网络。该项目将与DARPA嵌入式系统程序组合（PCES）倡议合作，以应用拟议的资源-平衡技术在这个项目中开发的传感器网络和分布式实时系统的国家重要性。教育的影响，拟议的研究包括integrationof先进的分布式系统的研究到本科生和研究生课程，以及推广活动，涉及高中学生到积极参与互联网规模的计算。

Hu/Vitek abstractLarge-scale compute-cycle sharing for complex and large scientificapplications is a long standing challenge in distributedcomputing. Many cycle-sharing systems have been developed and havedelivered orders of magnitude improvement in available resources.Nevertheless they are limited in their performance or capability.Furthermore, other forms of resource sharing and coordinationare needed to achieve truly distributed access to scientific infrastructure.The goal of this project is contribute to the national science andtechnology infrastructure by developing enabling technologies forvirtual laboratories open to researchers from all disciplines. Thisinfrastructure will leverage resources in peer-to-peer computing andprogramming languages to deliver an alternative architectural modelfor resource sharing over wide area networks. The self-organizingaspects of peer-to-peer networks promise to eliminate much of thedifficulty required to configure and maintain a large-scale globallydistributed computing and control system, and decentralization removes thepotential bottleneck and single point of failure of centralizedservice nodes. This project's contributions will be to provideabstractions for Peer-to-peer Computing based on extensions to theobject-oriented programming model and to develop a Peer-to-peerInfrastructure which extends the current peer-to-peer networksdeveloped for routing and data-centric applications.This project will work collaborativey with the DARPA ProgramComposition for Embedded Systems (PCES) initiative to apply the proposed resource-balancing techniques developed in this projectto sensor networks and distributed real-time systems of national importance.The educational impact of the proposed research includes integrationof advanced distributed systems research into both undergraduate andgraduate curricula, and outreach activities that involve high schoolsstudents into active participation in Internet-scale computing.