| Simulation is a useful tool for modeling logistics systems. However, simulation on its own is not an optimization tool. As a result, attempts have been made to combine simulation and optimization in commercially available software packages such as OptQuestRTM.; Optimization of a system through the use of simulation is difficult for several reasons. Due to the size and complexity of logistics systems, it is often necessary to consider the trade-offs between multiple conflicting performance measures for the system. One major drawback associated with tools such as OptQuestRTM is that users are not able to easily consider these trade-offs. To overcome this drawback, an ArenaRTM simulation model can be developed to employ multi-objective decision analysis techniques such as utility functions and value functions which can then be optimized.; This research will illustrate how a variety of criterion models can be interfaced with simulation models of logistics systems and the effect these different criterion models have on an optimal solution. The research will also investigate determining the best type of criterion model to use for a particular situation. Additionally, the research will include the programming and implementation of variance reduction techniques such as common random numbers and antithetic variates. The use of variance reduction techniques in combination with optimization methodologies does not seem to have been adequately addressed by commercial software packages. |
