Abstract
With the growth of mobile applications, user context becomes a dynamic but important factor for quality of service (QoS) in the cyber world. Many digital services have distinctly different performance under different service contexts. At runtime, an unexpected transition of user context may cause an application to fail to deliver the required QoS. In this paper, we propose a proactive service selection and reconfiguration approach to prevent service process failure. In our middleware support, a user's most probable context changes are actively predicted according to the current context state and historical data. Some backup service solutions for these anticipated state changes are then prepared. When the user context actually changes, the service process will be immediately routed to the preferred backup plan to prevent service disruption. We use a probabilistic graph model to describe the transition relationships between context attributes. The experimental results show that our context-aware proactive reconfiguration approach significantly improves the overall QoS under dynamically changing user context.