Complexity in embedded software systems has reached the point where we need run-time mechanisms that provide fault management services. Testing and verification may not cover all possible scenarios that a system encounters, hence a simpler, yet formally specified run-time monitoring, diagnosis, and fault mitigation architecture is needed to increase the software system’s dependability. The approach described in this talk borrows concepts and principles from the field of ‘Systems Health Management’ for complex aerospace systems and implements a two level health management architecture that can be applied in the context of a model-based software development process. The foundation of the architecture is a real-time component framework (built upon an ARINC-653 platform) that defines a specific model of computation for software components. The Component-level Health Manager (CHM) provides localized and limited service for managing the health of individual software components. A higher-level System Health Manager (SHM) manages the health of the overall system. SHM includes a diagnosis engine that uses a Timed Failure Propagation (TFPG) model derived from the component assembly; it reasons about fault effect cascades in the system, and it isolates the fault source components. Thereafter, the necessary system level mitigation action can be taken. The talk will discuss the reference architecture, including the modeling language, software generation, and the run-time platform used, and shows how the approach has been tested on selected examples.
Dr. Gabor Karsai is a Professor of Electrical Engineering and Computer Science at Vanderbilt University, and Senior Research Scientist at the Institute for Software-Integrated Systems. He has over twenty-five years of experience in software engineering. He conducts research in the design and implementation of embedded systems, in programming tools for visual programming environments, in the theory and practice of model-integrated computing, and in resource management and scheduling systems. He received his Diploma, MSc, and Dr. Techn. degrees from the Technical University of Budapest, Hungary, in 1982, 1984 and 1988, respectively, and his PhD from Vanderbilt University in 1988. He has published over 100 papers, and he is the co-author of four patents. He has managed several large research projects on model-based integration of embedded systems, on model-based toolchains, on fault-adaptive control technology, and on coordinated scheduling and planning.