In this paper, we present a simulation-based decision support system for solving the multi-echelon constrained inventory problem. The goal is to determine the optimal setting of stocking levels to minimize the total inventory investment costs while satisfying the expected response time targets for each field depot. We derive new decision support algorithms to be applied in different scenarios, including small-sample and large-sample cases. The first case requires that the set of alternative solutions is known at the beginning of the experiment, and the number of evaluated solutions may depend on the simulation budget (i.e.; the time available to solve the problem). In the second case, the alternative solutions are generated sequentially during the searching process, and we may terminate the algorithm when the specified sampling budget is exhausted. Empirical studies are conducted to compare the performance of the proposed algorithms with other conventional optimization approaches.
All Science Journal Classification (ASJC) codes