Ordinal Optimization Approach to Stochastic Simulation Optimization Problems and Applications

In this paper, we propose an ordinal optimization approach to solve for a good enough solution of the stochastic simulation optimization problem with huge decision-variable space. We apply the proposed ordinal optimization algorithm to G/G/1/K polling systems to solve for a good enough number-limited service discipline to minimize the weighting average waiting time. We have compared our results with those obtained by the existing service disciplines and found that our approach outperforms the existing ones. We have also used the genetic algorithm and simulated annealing method to solve the same stochastic simulation optimization problem, and the results show that our approach is much more superior in the aspects of computational efficiency and the quality of obtained solution.