• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Parallel and Distributed Systems >Timeliness-Accuracy Balanced Collection of Dynamic Context Data
【24h】

Timeliness-Accuracy Balanced Collection of Dynamic Context Data

机译：动态上下文数据的及时准确的平衡收集

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the future, we are likely to see a tremendous need for context-aware applications which adapt to available context information such as physical surroundings, network, or system conditions. We aim to provide a fundamental support for these applications - a real-time context information collection service. This service delivers the right context information to the right user at the right time. The complexity of providing the real-time context information service arises from 1) the dynamically changing status of information sources, 2) the diverse user requirements in terms of data accuracy and service latency, and 3) constantly changing system conditions. In this paper, we take into consideration these dynamics and focus on addressing the trade-offs between timeliness, accuracy, and cost for information collection in distributed real-time environments. We propose a middleware-based approach to enable a judicious composition of services for accuracy-aware scheduling and cost-aware database maintenance. Specifically, we characterize the problem in terms of quality-of-service satisfaction (QoSSat), quality-of-data satisfaction (QoDSat), and cost. We propose a middleware framework for the real-time information collection process, where the information mediator coordinates and facilitates communication between information sources and consumers. We design a family of algorithms for real-time request scheduling, request servicing, and directory service maintenance to be implemented at the mediator to support QoSSat and QoDSat. Our studies indicate that the composition of our proposed scheduling algorithm and directory service maintenance policy can improve the overall efficiency of the system. We also observe that the proposed policies perform very well as the system scales in the number of information sources and consumer requests
机译：将来，我们很可能会看到对上下文感知应用程序的巨大需求，这些应用程序可以适应可用的上下文信息，例如物理环境，网络或系统条件。我们旨在为这些应用程序提供基本支持-实时上下文信息收集服务。该服务在正确的时间将正确的上下文信息传递给正确的用户。提供实时上下文信息服务的复杂性源于1）信息源动态变化的状态，2）在数据准确性和服务等待时间方面不同的用户要求以及3）不断变化的系统条件。在本文中，我们考虑了这些动态因素，并着重解决了分布式实时环境中信息收集的及时性，准确性和成本之间的权衡问题。我们提出了一种基于中间件的方法，可以明智地进行服务组合，以进行准确性感知的调度和成本感知的数据库维护。具体来说，我们根据服务质量满意度（QoSSat），数据质量满意度（QoDSat）和成本来描述问题。我们为实时信息收集过程提出了一个中间件框架，其中信息中介者负责协调并促进信息源与消费者之间的通信。我们设计了用于实时请求调度，请求服务和目录服务维护的一系列算法，这些算法将在中介程序上实现以支持QoSSat和QoDSat。我们的研究表明，我们提出的调度算法和目录服务维护策略的组成可以提高系统的整体效率。我们还注意到，随着系统在信息源和消费者请求数量上的扩展，拟议政策的执行效果非常好

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号