통제변수 기반 Gradient를 이용한 확률적 최적화 기법 = Stochastic Optimization Method Using Gradient Based on Control Variates

다국어 초록 (Multilingual Abstract)

In this paper, we investigate an optimal allocation of constant service resources in stochastic system to optimize the expected performance of interest. For this purpose, we use the control variates to estimate the gradients of expected performance with respect to given resource parameters, and apply these estimated gradients in stochastic optimization algorithm to find the optimal allocation of resources. The proposed gradient estimation method is advantageous in that it uses simulation results of a single design point without increasing the number of design points in simulation experiments and does not need to describe the logical relationship among realized performance of interest and perturbations in input parameters. We consider the applications of this research to various models and extension of input parameter space as the future research.

참고문헌 (Reference)

1 권치명, "퍼터베이션 분석을 이용한 대기행렬 네트워크의 최적화" 9 (9): 89-102, 2000

2 Wilson, J. R, "Variance Reduction in Queueing Simulation Using Generalized Concomitant Variables" 19 : 129-153, 1984

3 Wieland J. R., "Stochastic gradient Estimation Using a Single Design Point" 390-397, 2006

4 Pritsker, A. A. B., "Simulation with Visual SLAM and AWeSim" John Wiley & Sons 1999

5 Andradottir,S., "Simulation Optimization" John Wiley & Sons 308-333, 1998

6 Ho, Y. C., "Perturbation Analysis of Discrete Event Dynamic Systems" Kluwer Academic Publishers 1991

7 Nozari, A., "Control Variates for Multi-population Simulation Experiments" 16 : 159-169, 1984

8 Kwon, C., "Combined Correlation Methods for Meta-model Estimation in Multi-population Simulation Experiments" 49 : 49-75, 1994

9 Anderson T.W, "An Introduction to Multivariate Statistical Analysis" John Wiley & Sons 1984

10 Robins, H, "A Stochastic Approximation Method" 32 : 400-407, 1951

11 Andradottir,S, "A New Algorithm for Stochastic Optimization" WSC 364-366, 1990