Tele-diagnosis: remote monitoring of large-scale systems

Modern systems such as high rise buildings, nuclear power plants, manufacturing facilities, battlefields, etc. are all examples of highly connected network enabled systems. Many of these systems need to be monitored round the clock for high availability. Such systems typically consist of embedded sensors in networked subsystems that can transmit data to central (or remote) monitoring stations. In this paper, we present a distributed diagnosis solution that will not only monitor these sensor data streams, but also troubleshoot and diagnose subsystem failures, automatically, and in realtime. We present the software architecture that adapts TEAMS-RT-our real-time, embeddable diagnostic reasoner-into a distributed monitoring and diagnosis framework for tele-diagnosis of large, complex systems. This is followed by a description of the individual modules of the architecture, their interactions captured in time-sequence diagrams, and simulation results. Finally, we highlight some of our current and future research in the area.