Transient Fault Tolerance

01.07.2006 - 31.08.2010
Research funding project
The purpose of this project is to examine how transient faults can be captured in models of distributed real-time computing, and how to tolerate them in an effective manner. Here effectiveness is related to both time and space, i.e., the time it takes until all consequences of a transient fault are removed from the system and the number of processes it takes w.r.t. the assumed upper bound on the number of (concurrent) transient failures. Transient failures are of primary concern for aerospace applications. They are also a major source of failure in other networked embedded systems, in particular in automotive applications. Actually, the importance of tolerating transient faults goes way beyond networked embedded systems: Applications in large scale dynamic systems, e.g., sensor networks, need to cope with such phenomena.

People

Project leader

Project personnel

Institute

Grant funds

  • FFG - Österr. Forschungsförderungs- gesellschaft mbH (National) Austrian Research Promotion Agency (FFG)

Research focus

  • Computer Engineering: 100%

Keywords

GermanEnglish
Fehlertoleranzfault tolerance
Verteilte AlgorithmenDistributed Algorithms

Publications