在現今瞬息萬變的環境下，決策者總是希望能快速的解決問題，於是如何提供決策者一個快速、有效的解決方法便是一項重要議題。本研究針對多階層存貨系統問題發展演算法，此存貨系統包含總倉維修中心與多個服務站，當零件損壞時，服務站扮演服務顧客的角色，提供新的替代品給顧客，並根據存貨政策補貨。總倉維修中心則扮演補貨中心及維修中心的角色，負責將服務站送來之損壞零件維修好。在此存貨系統中，顧客需求的間隔時間、運輸時間及維修時間皆為隨機性的變數。

　　本研究發展兩個決策支援演算法，分別為小樣本演算法及大樣本演算法。小樣本演算法考量在有限資源、時間下，僅能評估少量的解個數。一個解之所有服務站等候時間皆低於預定指標值，即為可行解。當存在可行解時，小樣本演算法會找出存貨投資成本最小的為最佳解。然而，當無可行解時，此時目標函數由存貨投資成本與限制式違背量懲罰成本組成，小樣本演算法將透過排序與選擇程序(Ranking and Selection；R&S)選出一最適解。大樣本演算法是以隨機限制化基因演算法為基礎，結合可行性驗證程序(Feasibility Check Procedure；FCP)，解決具確定性目標函數及多個隨機限制式問題之最佳化演算法，搜尋龐大的可行解空間，期望找出一最佳解，此最佳解必須滿足所有服務站等候時間的限制，並最小化存貨投資成本。

In this changing environment, decision makers always hope to solve the problem as soon as possible. Therefore, it is an important issue to provide a useful and efficient method to decision makers. In our research, we focused on multi-echelon inventory system which included one warehouse repair center and multiple field depots. On one hand, when customer arrived with nonfunctional parts, depots will provide new parts to customers and replenish inventory according to the inventory policy. On the other hand, warehouse repair center is responsible for repairing the parts and replenishing the inventory of the depots. In our inventory system, we consider the part interfailure time, transportation time and
repair time as random variables.

We developed two decision support algorithms, small sample algorithm and large sample algorithm, respectively. Small sample algorithm is used to solve the problem when we could evaluate few solutions due to the limited cost and time. A solution is feasible when all constraints are satisfied. When there are feasible solutions, small sample algorithm will choose one solution with minimal inventory investment cost as best. On the contrary, when there are no feasible
solutions, the objective function is composed of inventory
investment cost and penalty cost. And then small sample algorithm will choose the solution with minimal total cost as compromise one through ranking and selection procedure. Large sample algorithm is one kind of optimization algorithm, combined with stochastic constrained genetic algorithm and feasibility check procedure to solve the problem with deterministic objective function and multiple
stochastic constraints. Through searching huge solution space, large sample algorithm will find a best solution which must fulfill all the constraints and with minimal inventory investment cost.

Andrad´ottir S. and Kim, S. H. (2010) Fully Sequential Procedures for Comparing Con-strained Systems via Simulation. Naval Research Logistics, 57, 403–421.

Axs¨ater, S. (1990) Simple Solution Procedures for a class of Two-Echelon Inventory Prob-lems. Operations Research, 38, 64–69.

Batur, D. and Kim, S.H. (2006) Fully sequential selection procedures with parabolic boundary. IIE Transactions, 38, 749–764.

Batur, D. and Kim, S.H. (2010) Finding Feasible Systems in the Presence of Constraints on Multiple Performance Measures. ACM Transactions on Modeling and Computer Simulation, forthcoming .

Boesel, J., Nelson, B.L. and Ishii, N. (2003) A Framework for Simulation-Optimization Software. IIE Transactions, 35, 221–230.

Boesel, J., Nelson, B.L. and Kim, S.H. (2003) Using Ranking and Selection to ”Clean up” after Simulation Optimization. Operations Research, 51, 814–825.

Butler, J., Morrice, D.J. and Mullarkey, P.W. (2001) A Multiple Attribute Utility Theory Approach to Ranking and Selection, Management Science, 47, 800–816.

Caggiano, K.E., Jackson, P.L., Muckstadt, J.A. and Rappold, J.A. (2007) Optimizing Ser-vice Parts Inventory in a Multi-Echelon, Multi-Item Supply Chain with Time-Based Customer Service Level Agreements. Operations Research, 55, 303–318.

Caggiano, K.E., Jackson, P.L., Muckstadt, J.A. and Rappold, J.A. (2009) Efficient Com-putation of Time-Based Customer Service Levels in a Multi-Item, Multi-Echelon Sup¬ply Chain: A Practical Approach for Inventory Optimization. European Journal of Operational Research, 199, 744–749.

Caglar, D., Li, C.-L. and Simchi-Levi, D. (2004) Two-Echelon Spare Parts Inventory System Subject to a Service Constraint. IIE Transactions, 36, 655–666.

Carrizosa, E. and Romero-Morales, D. (2001) Combining Minsum and Minmax: A Goal Programming Approach. Operations Research, 49, 169–174.

Cezik, M. T. and L’Ecuyer, P. (2008) Staffing Multiskill Call Centers via Linear Program-ming and Simulation. Management Science, 54, 310–323.

Fu, S.Y. (2011) Discrete Optimization via Simulation Algorithm Considering Single Sto-chastic Constraint. Unpublished Dissertation, National Cheng Kung University.

Graves, S.C. (1985) A Multi-Echelon Inventory Model for a Repairable Item with One-for-One Replenishment. Management Science, 31, 1247–1256.

Hong, L.J. and Nelson, B.L. (2005) The Tradeoff Between Sampling and Switching: New Sequential Procedures for Indifference-zone Selection. IIE Transactions, 37, 623–634.

Hong, L.J. and Nelson, B.L. (2009) A Brief Introduction to Optimization via Simulation. Winter Simulation Conference Proceedings, 75–85.

Hopp, W.J., Zhang, R.Q. and Spearman, M.L. (1999) An Easily Implementable Hierar¬chical Heuristic for a Two-Echelon Spare Parts Distribution System. IIE Transactions, 31, 977–988.

Hyunjung, L., Yongduek, Seo. and Sang Wook, Lee (2010) Removing Outliers by Mini-mizing the Sum of Infeasiblilities. Image and Vision Computing, 28, 881–889.

Kim, S.H. and Nelson, B.L. (2001) A Fully Sequential Procedure for Indifference-Zone Selection in Simulation. ACM Transactions on Modeling and Computer Simulation, 11, 251–273.

Kim, S.H. and Nelson, B.L. (2005) Selecting the Best System,Chapter 17 in Elsevier Handbooks in Operations Research and Management Science: Simulation , Elsevier, forthcoming.

Lee, H.L. and Moinzedeh, K. (1987) Two-Parameter Approximations for Multi-Echelon Repairable Inventory Models With Batch Ordering Policy. IIE Transactions, 19, 140–149.

Moinzedeh, K. and Lee, H.L. (1986) Batch Size and Stocking Levels in Multi-Echelon Repairable Systems. Management Science, 32, 1567–1581.

Muckstadt, J.A. (1973) A Model for a Multi-Item, Multi-Echelon, Multi-Indenture Inven-tory System. Management Science, 20, 472–481.

Muckstadt, J.A. and Thomas, L.J. (1980) Are Multi-Echelon Inventory Methods Worth Implementing in Systems with Low-Demand-Rate Items? Management Science, 26, 483–494.

Ogryczak.W (2001). Comments on Properties of the Minmax Solutions in Goal Program-ming. European Journal of Operation Research, 132, 17–21.

Pichitlamken, J., Nelson, B.L. and Hong, L.J. (2006) A Sequential Procedure for Neigh-borhood Selection-of-the-Best in Optimization via Simulation, European Journal of Operation Research, 173, 283–298.

Rinott, Y. (1978) On Two-stage Selection Procedures and Related Probability-Inequalities. Communications in Statistics–Theory and Methods, A7, 799-811.

Santner T.J. and Tamhane, A.C. (1984) “Designing experiments for selecting a normal population with a large mean and a small variance,” Design of Experiments – Rank¬ing and Selection: Essays in Honor of Bechhofer R. E., Santer T.J. and Tamhane A.C. (Editors), Marcel-Dekker, New York, 179–198.

Sherbrooke, C.C. (1968) METRIC: A Multi-Echelon Technique for Recoverable Item Control. Operations Research, 16, 122–141.

Sherbrooke, C.C. (1986) VARI-METRIC: Improved Approximations for Multi-Indenture, Multi-Echelon Availability Models. Operations Research, 34, 311–319.

Verma, M. K., Shrivastava, R. K. and Tripathi, R. K. (2010) Evaluation of Minmax, Weighted and Preemptive Goal Programming Techniques with Reference to Mahanadi Reservoir Project Complex. Water Resour Manage, 24, 299–319.

Wang, Y., Cohen, M.A. and Zheng, Y.-S. (2000) A Two-Echelon Repairable Inventory System with Stocking-Center-Dependent Depot Replenishment Lead Times. Man-agement Science, 46, 1441–1453.

Xu, J., Hong, L. J., Nelson, B. L., 2010. Industrial strength COMPASS: A Comprehen¬sive Algorithm and Software for Optimization via Simulation. ACM Transactions on Modeling and Computer Simulation, 20, 1-29.

Yang, J. (2000) Minimax Reference Point Approach and its Application for Multiobjec¬tive Optimisation. European Journal of Operational Research, 126, 541–556.

Yang, J. (2008) Infeasibility Resolution Based on Goal Programming. Computers & Op-erations Research, 35, 1483–1493.