A new approach for parallel steady-state simulations

We propose a new procedure for building confidence interval estimators of steady-state parameters in discrete event simulations. The procedure uses parallel processors to generate independent replications and constructs the confidence interval estimator by solving a generalized least square problem. The most appealing theoretical feature of the proposed procedure is that the precision of the resulted estimator can be improved by simply increasing the number of processors (or independent replications) while the simulated time length is fixed on an appropriate level on each processor. Experiments conducted on M/M/1 queue waiting time processes in heavy traffic confirm this theoretical property.