Fault-tolerant behavior in state-of-the-art grid workflow management systems

While the worko w paradigm, emerged from the eld of business processes, has been proven to be the most successful paradigm for creating scientic applications for execution also on Grid infrastructures, most of the current Grid worko w management systems still cannot deliver the quality, robustness and reliability that are needed for widespread acceptance as tools used on a day-to-day basis for scientists from a multitude of scientic elds. This paper introduces the current state of the art in fault tolerance techniques for Grid worko w systems. The examined categories and the summary of current solutions reveal future directions in this area and help to guide research towards open issues.