A GENERALIZED STOCHASTIC HIGH-LEVEL PETRI-NET MODEL FOR PERFORMANCE ANALYSIS

We present a generalized stochastic high-level Petri net (GSHLPN) mode l for evaluating the performance of parallel/distributed systems. In o ur model, we have classified the transitions of the predicate/transiti on nets (PrT-nets) into two types: timed predicate transitions with ex ponentially distributed firing times and immediate predicate transitio ns with zero firing times. Also, the PrT-nets are extended by includin g inhibitor predicate arcs. The motivation for introducing these new c onstructs in the GSHLPN model is discussed. The model is developed to be a hybrid of the PrT-net and generalized stochastic Petri net models . We define the GSHLPN model and show how performance estimates are ob tained from the GSHLPN model. To manage the complexity of large system s, we have reduced the size of the reachable state space by combining the GSHLPN model with the compound marking technique (CMT). We show ho w the GSHLPN model with the CMT can be useful for the performance anal ysis of complex systems, such as hypercube multicomputer systems. Fina lly, we investigate another approach to further reduce the size of the state space of this model by applying two different types of aggregat ion techniques on the GSHLPN model: time scale decomposition technique and CMT. This aggregation concept is illustrated through the example of a degradable Star multicomputer system. (C) 1997 by Elsevier Scienc e Inc.