CAREER: Towards an Efficient Ubiquitous Computing Infrastructure

职业：迈向高效、普适的计算基础设施

• 批准号: 0092678
• 负责人: Srinivasan Seshan
• 金额: $ 48.77万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-06-01 至 2007-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0092678&HistoricalAwards=false
• 关键词: CAREER; Towards; Efficient; Ubiquitous; Computing

In 1989, the researcher applied for graduate schooland wrote that global network access would change the way people work and that people would use the network to "plan travel, pay bills and access libraries of information". A decade later, the Internet and Web applications made these network applications a reality. As we look to the future, the next major evolution in technology will be to make it possible for users to access information and interact with all devices in their environment through ubiquitous wireless networks and simple inexpensive computing devices such as PDAs [81]. The popular approach to achieving this future vision has been to move the applications and network services available on the Internet onto the simple mobile devices and the wireless network infrastructure. However, innovative network services and protocols will be necessary to operate such networks and applications efficiently. The objective of this NSF CAREER proposal is to examine the services that this new generation of mobile applications need from the network and to carefully adapt the design and implementation of these services to the environment's demands. The unique requirements of this environment include: Power Awareness. Most mobile devices will be battery operated and thus require energy efficiency. Wireless Link Characteristics. Wireless links are slower due to limited spectrum availability, are prone to loss and disconnection, and are often connection-oriented or stateful. Network Evolution. Since users will not upgrade all their small devices simultaneously, the future system must support automatic upgrading, multiple simultaneous versions and/or backward compatibility. Dynamic Network. The members of a network are dynamic due to mobility and range of network. Isolation. A group of wireless devices should be able to operate in isolation from any infrastructure. Simple Devices. Many of the devices that participate in such a network may be extremely simple. Scale of Operation. The future network will have billions of small devices. New Applications. Applications in this environment may need very different services from the network. The objective of this CAREER proposal is to design a new networking and operating system infrastructure for this next generation of ubiquitous computing applications. The research plan consists of three major stages. In the first stage, the researcher plans to build some of these next generation applications to improve the understanding of their requirements. The next stage consists of developing protocols and operating system services based on these new requirements. The project is especially interested in 1) improving the bandwidth and power efficiency of network protocols, 2) making it possible for applications and protocols to adapt to the availability of power, availability of bandwidth and other environmental conditions, 3) designing service discovery approaches that can handle the query types that are likely for mobile applications, and 4) making this environment support the easy introduction of new link technologies, network protocols and applications. Finally, the research will be evaluated by modifying our test applications to use these new services. If successful, this project will significantly change how wireless networks and mobile applications of the future will be structured and built. The education plan proposes to use educational applications such as shared note taking [24] and intelligent classrooms [1] among the early target applications to be used. In addition, the researcher plans to incorporate mobile and wireless education into the already existing mainstream undergraduate and graduate networking classes.

1989年，这位研究员申请了研究生院，并写道，全球网络接入将改变人们的工作方式，人们将利用网络“计划旅行、支付账单和访问信息图书馆”。十年后，互联网和Web应用程序使这些网络应用成为现实。展望未来，技术的下一个主要发展将是使用户能够通过无处不在的无线网络和简单廉价的计算设备（如PDA）访问信息并与环境中的所有设备进行交互。实现这一未来愿景的流行方法是将Internet上可用的应用程序和网络服务移动到简单的移动的设备和无线网络基础设施上。然而，创新的网络服务和协议将是必要的，以有效地操作这样的网络和应用。 本NSF CAREER提案的目标是研究新一代移动的应用程序需要从网络中获得的服务，并仔细调整这些服务的设计和实现以满足环境的需求。这种环境的独特要求包括： 权力意识。大多数移动的设备将由电池供电，因此需要能效。 无线链路特性。无线链路由于有限的频谱可用性而较慢，易于丢失和断开，并且通常是面向连接或有状态的。 网络演进。由于用户不会同时升级所有小型设备，未来的系统必须支持自动升级、多个同步版本和/或向后兼容。 动态网络。由于网络的移动性和范围，网络的成员是动态的。 隔离一组无线设备应该能够独立于任何基础设施运行。 简单的设备。参与这种网络的许多设备可能非常简单。 经营规模。未来的网络将拥有数十亿个小型设备。 新的应用程序。这种环境中的应用程序可能需要非常不同的网络服务。 本CAREER提案的目标是为下一代无处不在的计算应用程序设计一个新的网络和操作系统基础设施。研究计划包括三个主要阶段。在第一阶段，研究人员计划构建一些下一代应用程序，以提高对它们需求的理解。下一阶段包括基于这些新需求开发协议和操作系统服务。该项目特别感兴趣的是1）提高网络协议的带宽和功率效率，2）使应用和协议能够适应功率的可用性、带宽的可用性和其他环境条件，3）设计能够处理可能用于移动的应用的查询类型的服务发现方法，以及4）使该环境支持新的链路技术、网络协议和应用的容易引入。最后，将通过修改我们的测试应用程序来使用这些新服务来评估研究。如果成功，该项目将显著改变未来无线网络和移动的应用程序的结构和构建方式。 教育计划建议使用教育应用程序，如共享笔记[24]和智能教室[1]，这些应用程序是早期使用的目标应用程序。此外，研究人员计划将移动的和无线教育纳入已经存在的主流本科生和研究生网络课程。