Dynamic window-based adaptive fault monitoring for ubiquitous computing systems

A number of different kinds of applications in large and complex ubiquitous computing systems need fault tolerance. Here failure detection is one of the key elements for efficient fault management. There exist various fault monitoring and detection algorithms employing a timeout-based mechanism. However, they are occasionally inaccurate in unstable or overloaded system. The goal of the proposed scheme is to enhance the accuracy of fault detection by properly handling the monitoring interval. This is achieved by dynamically adjusting the window of the past elapsed times included in the prediction of the monitoring interval. Computer simulation reveals that the proposed algorithm allows much more elastic and accurate prediction of monitoring interval than the existing algorithms regardless of load condition of the system.