Steady state solution of MRSPN with mixed preemption policies

Markov Regenerative Stochastic Petri Nets (MRSPN) have been recently recognized as a valuable tool to model systems with non-exponential timed activities. The usual assumption in the implementation of such models is that at most a single non-exponential transition, with associated enabling memory policy, can be enabled in each marking. More recently, new memory policies have been studied in order to represent more complex and effective preemption mechanisms in real systems. Closed-form solutions in the Laplace transform domain have been provided also in this case. This paper concentrates on the steady-state analysis of MRSPN and provides an unified analytical approach to include mixed memory policies into a single model. A numerical example concludes the paper