Collaborative Research: CSR-EHCS, SM: DPOP - A Dynamic Profiling and Optimization Platform for Sensor-Based Networks

合作研究：CSR-EHCS、SM：DPOP - 基于传感器的网络的动态分析和优化平台

• 批准号: 0834080
• 负责人: Ann Ramirez
• 金额: --
• 依托单位: University of Florida
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2008
• 资助国家: 美国
• 起止时间: 2008-08-15 至 2011-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0834080&HistoricalAwards=false
• 关键词: Collaborative; Research; CSR; EHCS; SM

Sensor-based platforms are enabling the vision of ubiquitous computing environments to be realized. However, as these platforms continue to evolve, they are becoming increasingly complex to design and implement for a given application. Much of the complexity associated with sensor-based platforms is due to the plethora of parameters that must be considered. To further complicate matters, application developers oftentimes are not trained engineers, but rather biologists, teachers, or agriculturists who wish to utilize the sensor-based systems within their given domain. Faced with an overwhelming number of choices, application design may be a daunting task for non-experts. This project seeks to alleviate some of the complexities associated with sensor-based system design through the use of automated optimization methods that abstract many of the underlying design and platform details, dynamic profiling methods capable of observing application-level behavior, and dynamic optimization to tune the underlying platform accordingly. Dynamic profiling enables an accurate view of the application behavior and allows the system to monitor how the application responds to changing environmental conditions or changes in the platform itself. If the developer specified performance metrics are not currently being met, dynamic optimization and network reconfiguration can adapt the deployed network to its current surroundings and application requirements. This dynamic profiling and optimization environment reduces developer effort and increases the accessibility of sensor-based systems to a wider audience, where we believe such systems can enhance everyday lives, and further the emergence of innovative applications.

基于传感器的平台使普适计算环境的愿景得以实现。然而，随着这些平台的不断发展，为给定的应用程序设计和实现它们变得越来越复杂。与基于传感器的平台相关的许多复杂性是由于必须考虑过多的参数。使问题进一步复杂化的是，应用程序开发人员通常不是训练有素的工程师，而是希望在其给定领域内利用基于传感器的系统的生物学家、教师或农业学家。面对大量的选择，应用程序设计对于非专业人士来说可能是一项艰巨的任务。该项目旨在通过使用抽象了许多底层设计和平台细节的自动化优化方法、能够观察应用程序级行为的动态分析方法以及相应地调整底层平台的动态优化，减轻与基于传感器的系统设计相关的一些复杂性。动态分析可以准确地查看应用程序的行为，并允许系统监视应用程序如何响应不断变化的环境条件或平台本身的变化。如果开发人员指定的性能指标目前没有得到满足，动态优化和网络重新配置可以使已部署的网络适应其当前环境和应用程序需求。这种动态分析和优化环境减少了开发人员的工作量，并增加了基于传感器的系统对更广泛受众的可访问性，我们相信这样的系统可以改善日常生活，并进一步推动创新应用程序的出现。