NMI: Exploration of Middleware Technologies for Ubiquitous Computing with Applications to Grid Computing

NMI：普适计算中间件技术及其在网格计算中的应用探索

• 批准号: 0330639
• 负责人: Umakishore Ramachandran
• 金额: --
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-09-15 至 2008-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0330639&HistoricalAwards=false
• 关键词: NMI; Exploration; Middleware; Technologies; Ubiquitous

The proposed research is to investigate middleware technologies for ubiquitous computing, and under a partnership with HP Labs, extend those technologies to support interactive applications on the grid. The following research contributions are expected:* Develop attribute-based naming and discovery of resources;* Develop novel techniques for higher-level data fusion leading to synthesis of resources where applicable;* Develop novel techniques for recovering from failures (both real and perceived performance);* Develop novel resource allocation strategies that take into account a variety of parameters including time-varying load on participating resources, dynamic user demands, and location information; and* Undertake detailed scalability studies of the proposed techniques in the context of ubiquitous computing applications.A concrete deliverable beyond these research nuggets will be the incorporation of this middleware technology into standard grid computing infrastructure such as the Globus toolkit in partnership with HP labs.The location-aware middleware will be demonstrated in two ways: campus-based outdoor activity support based on the Georgia Tech campus and the Aware Home, a unique laboratory for the investigation of ubiquitous computing in a domestic setting.The work has broad impact and intellectual merit with respect to its potential for adoption and use via Globus integration and industry partnership.

这项研究的目的是研究用于普适计算的中间件技术，并与HP实验室合作，扩展这些技术以支持网格上的交互式应用。预计将做出以下研究贡献：* 开发基于属性的资源命名和发现;* 开发用于更高级别的数据融合的新技术，从而在适用的情况下合成资源;* 开发用于从故障中恢复的新技术（包括真实的和感知的业绩）;* 制定新的资源分配策略，考虑到各种参数，包括参与资源的时变负载，动态用户需求，和位置信息;以及 * 在普适计算应用程序的环境中对所提出的技术进行详细的可扩展性研究。除了这些研究成果之外，一个具体的可交付成果将是将这种中间件技术结合到标准的网格计算基础设施中，例如与HP实验室合作的Globus工具包。位置感知中间件将通过两种方式进行演示：基于格鲁吉亚理工学院校园和Aware Home的校园户外活动支持，Aware Home是一个独特的实验室，用于调查家庭环境中的普适计算。这项工作具有广泛的影响力，并通过Globus集成和行业合作伙伴关系对其进行采用和使用。