A method for reducing the variance of simulation-generated estimates is proposed and discussed. The method may be applied to the estimation of steady state parameters of discrete and continuous time Markov chains, semi-Markov processes, and regenerative discrete time Markov processes on a general state space (such as the waiting time process in a multiple-server queue). The method is similar to the technique of control variables, but differs in that the means of the controls need not be explicitly known. Numerical results for a variety of simple queueing models are presented.
Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.