QoS management in Web-based real-time data services

Abstract

The demand for real-time data services has been increasing recently. Many e-commerce applications and web-based information services are becoming very sophisticated in their data needs. They span the spectrum from low level status data, e.g., stock prices, to high level aggregated data, e.g., recommended selling/buying point. In these applications, it is desired to process user requests within their deadlines using fresh data, which reflect the current market status. Current web-based data services are poor at processing user requests in a timely manner using fresh data. To address this problem, we present a framework for guaranteed real-time data services in unpredictable environments. We also introduce a possible application of our approach in the distributed environment.