Bounding asymptotic dependability and performance measures

One of the major drawbacks of Markov models is the size of the generated state space. Often its high value (sometimes infinite) makes the numerical analysis impossible to perform. A possible approach to deal with this problem is to bound the measures of interest. In recent years, some methods have been proposed in this direction, mainly for stationary dependability measures. In this paper, we propose a new approach which can be applied in more general conditions than previous ones. It allows, in particular, to derive performance measures of some analytically intractable queuing models. We illustrate it with examples of open models of tandem queues with blocking.