Using Petri nets for the design of conversation boundaries in fault-tolerant software

Only a few mechanisms have been proposed for the design of fault-tolerant software. One of these is the conversation, which, though it has some drawbacks, is a potentially promising structure. One of the problems with conversations is that they must be defined and verified by the user. In this short note, a systematic method for generating the boundaries of conversations directly from the specification is proposed. This method can also be used to verify conversations selected by the user. The specification is described by a high-level modified Petri net which can easily be transformed into a state model called an action-ordered tree. The conversation boundaries are then determined from this tree. It is proved that the method proposed is complete in the sense that all of the possible boundaries can be determined, and it has the merit of simplicity. A robot arm control system is used to illustrate the idea. The proposed method can serve as the basis of a tool to assist in conversation designs