Treffer: Timeliness-Accuracy Balanced Collection of Dynamic Context Data.

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. [ABSTRACT FROM AUTHOR]

Copyright of IEEE Transactions on Parallel & Distributed Systems is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)