Approximate Simulation Budget Allocation for Selecting the Best Design in the Presence of Stochastic Constraints

Abstract

We develop a new Optimal Computing Budget Allocation (OCBA) approach for the ranking and selection problem with stochastic constraints. The goal is to maximize the probability of correctly selecting the best feasible design within a fixed simulation budget. Based on some approximations, we derive an asymptotic closed-form allocation rule which is easy to compute and implement and can help provide more insights about the allocation. The numerical testing shows that our approach can enhance the simulation efficiency.