Computation of the Distribution of Accumulated Reward with Fluid Stochastic Petri-Nets

摘要

We describe the recently introduced Fluid Stochastic Petri-Nets as a means ofcomputing the distribution of the accumulated rate reward in a GSPN. In practice, it is the expected value of a reward which is computed, a quantity which is dependent solely on the solution of the underlying Markov chain. Until now, the instantaneous reward rates have been a function of the GSPN marking only, and the Markov chain itself was not influenced by the development of the reward value. In this paper it is shown that FSPNs may be used to simulate GSPN reward models and that they allow an important generalization in that both the firing rates of the GSPN and the reward rate may depend on the current reward value. Example models of repairable systems are used to demonstrate the additional capabilities.