"The non-sequential method, though using less memory and CPU time, cannot directly provide frequency and duration indices. A state transition sampling technique is presented which can be used to estimate the actual frequency index without requiring an additional enumeration procedure. This approach does not involve sampling component up and down cycles and storing chronological information on the system state, as the next system state is obtained by allowing a component to undergo transitions from its present state." (Roy Billinton, Annapoorani Sankarakrishnan 1994)
As for the sequential MCS, can be used to accurately calculate the actual frequency indices and can incorporate any state residence time distribution.
See the attached material, the part which is about MCS.
There are two types of Monte Carlo simulation: non-sequential (or random) Monte Carlo (using states of the system) and sequential Monte Carlo (chronological).
The difference between non-sequential Monte Carlo simulation and sequential Monte Carlo simulation is in the way in which the states of the system are selected to be simulated. The non-sequential (random) approach simulates the states of the system over the duration of its live, by choosing the states randomly. The concept of time does not appear. The simulation of the period of service is reproduced a great number of times, to obtain statistically reliable averages of the results. In this case, the results are obtained by separately simulating each state of the system. The states of the system depend on the combination of the states of its components. Each state of a component is given according to the probability that the component appears in this state.
The sequential (chronological) approach simulates the states of the system in chronological order as the states of its components change. Chronological modeling is related to the assessment of series (or sequences) of states of the system in the stochastic process of the course of its operation (simulation of the "life" of the system) over a given period of service (for example one year). The simulation of the period of service is reproduced a great number of times to obtain statistically reliable averages of the results.