A decomposition approach for analysis of parallel processing systems

Abstract

Traditional approaches to reliability and performance analysis become intractable when dealing with complex parallel and distributed processing systems, computer networks, and software for such systems. New approaches based on Petri nets, dataflow graphs, simulations and approximations are now used in such cases. In order to extend the utility of Petri nets and dataflow graphs, the authors present a decomposition technique that can be used to partition a large system into smaller subsystems, where performance indexes of the total system can be obtained (at least approximately) from the subsystem analyses. The decomposition reduces the computational complexity of analysis significantly. The approach (using marked graph components) is similar to the concept of 'near-completely decomposable' stochastic processes. >