存貨管理問題在供應鏈的領域中是一個重要的議題，其策略為要如何保持存貨的數量以及訂購次數的平衡，若一個企業擁有良好的存貨管理策略，將能夠有效地提高其營業利潤。存貨管理問題主要是以成本為導向，探討在何種訂購策略下能夠有較高的經濟效益，由於環境的改變，顧客在供應鏈上的地重要度逐漸提高，因此顧客滿意度也越來越重要，近年來，存貨管理問題逐漸轉變為考量多個目標，在顧客滿意度與成本之間取得平衡。而在存貨管理問題中，顧客何時到來、運送貨品需要多久時間、顧客的需求數量為何、產品因人為或環境因素而產生損壞等等，皆屬於隨機性的因子，一般的數學模式難以處理這些具有隨機性因子的問題。
為了考量具有隨機因子之多目標問題，本研究運用模擬最佳化發展了兩種方法
來求解多目標存貨問題，分別採用多目標最佳化方法中後驗式(Posterior articulation of preference)以及逐步式(Progressive articulation of preference)方法的概念。後驗式方法為先產生問題的柏拉圖解集合，決策者便可從此集合獲得最佳解的相關資訊，分析並進行評估，接著便可以從此集合內挑選出一滿意且適宜的決策當做最佳策略。而逐步式方法則為在求解的過程中，藉由與決策者互動來逐步修正問題的參數，並改善當前的可行解，最後便可獲得令決策者滿意之最佳策略。對於上述兩種方法，本研究在最後也將針對抽樣成本、時間成本、正確選擇機率(PCS) 與目標績效值之優劣，分析在何種情境下，採用何種方法能有較佳的解題效率。

In this research we combine the concept of multi-objective optimization and a method of simulation optimization to solve a multi-objective inventory problem. We have developed two methods for a multi-objective inventory problem which contains the stochastic factor. In the first, we have adopted the concept of posterior articulation of preference, using the ɛ-constraint method to generate the non-dominated solution set, and then found the best policy from this set. For the second method we adopted the concept of progressive articulation of preference. With pairwise comparisons, we modified the parameters and continued to solve the problem progressively to find the best solution from the candidate solutions. Through empirical evaluation we compared the two methods, and found which gave the better performance in the specific situations. The results show that when the number of candidate solutions is small, the ɛ-constraint method returns better performance, and it can provide the non-dominated solutions set for the Decision maker. With this information, the Decision maker can make decisions more correctly. However, when the number of candidate solutions is large, the ɛ-constraint method returns poor performances, so we can use the pairwise comparisons method in this situation. We have also developed two methods for the multi-objective inventory problem, which are different from other existing multi-objective programming methods. Our methods can deal with complex factors and provide statistical guarantees.

References
[1] S. Andrad´ottir and S. H. Kim, “Fully sequential procedures for comparing constrained systems via simulation,” Nav. Res. Logist., vol. 57, no. 5, pp. 403–421,
2005.
[2] F. B. Abdelaziz, B. Aouni and R. E. Fayedh, “Multi-objective stochastic programming for portfolio selection,” Eur. J. Oper. Res., vol. 177, no. 3, pp. 1811–1823, 2007.
[3] A. Azaron, K. N. Borwn, S. A. Tarim and M. Modarres, “A multi-objective stochastic programming approach for supply chain design considering risk,” Int. J. Prod. Econ., vol. 116, no. 1, pp. 129–138, 2008.
[4] P. J. Agrell, “A multicriteria framework for inventory control,” Int. J. Prod. Econ., vol. 41, no. 1, pp. 59–70, 1995 .
[5] J. Andersson, “A survey of multiobjective optimization in engineering design,” Tech. Rep. LiTH-IKP-R-1097, Dept. Mech. Eng., Link¨oping Univ., Link¨oping, Sweden, 2000.
[6] S. Bashyam and M. C. Fu, “Optimization of (s, S) inventory systems with random lead times and a service level constraint,” Manage. Sci., vol. 44, no. 12, pp. 243–256, 1998.
[7] J. Boesel, L.N. Barry and S.H. Kim, “Using ranking and selection to clean up after simulation optimization,” Oper. Res., vol. 51, no. 5, pp. 814–825, 2003 .
[8] D. Batur and S. H. Kim, “Finding feasible systems in the presence of constraints on multiple performance measures,” ACM Trans. Model. Comput. Simul., vol. 20, no. 3, 2010.
[9] D. Batur and S. H. Kim, “Fully sequential selection procedures with parabolic boundary,” IIE Trans., vol. 38, no. 9, pp. 749–764, 2006.
[10] J. Butler, D. J. Morrice and P.W. Mullarkey, “A multiple attribute utility theory approach to ranking and selection,” Manage. Sci., vol. 47, no. 6, pp. 800–816, 2001.
[11] R. Benayoun, J. De Montgolfier, J. Tergny and O. Laritchev, “Linear programming with multiple objective functions: Step method (STEM),” Math. Program., vol. 1, no. 1, pp. 366–375, 1971.
[12] R. E. Bechhofer, “A single-sample multiple decision procedure for ranking means of normal populations with known variances,” Ann. Math. Stat., vol. 25, no. 1, pp. 16–39, 1954.
[13] F. F. Baesler and J. A. Sep´ulveda, “Multi-Objective Simulation Optimization for a Cancer Treatment Center,” in Proc. Winter Simulation Conf., Virginia, USA, 2001, pp. 1405–1411.
[14] L. Cheng, E. Subrahmanian and A. W. Westerberg, “Multiobjective decisions on capacity planning and production-inventory control under uncertainty,” Ind. Eng.
Chem. Res., vol. 43, no. 8, pp. 2192–2208, 2004.
[15] A. Chen and X. Xu, “Goal programming approach to solving network design problem with multiple objective and demand uncertainty,” Expert Syst. Appl., vol. 39, no. 4, pp. 4060–4170, 2012.
[16] R. B. Franca, E. C. Jones, C. N. Richards and J. P. Carlson, “Multi-objective stochastic supply chain modeling to evaluate tradeoffs between profit and quality,” Int. J. Prod. Econ., vol. 127, no. 2, pp. 292–299, 2010.
[17] P. I. Frazier and A. M. Kazachkov, “Guessing preferences: a new approach to multiattribute ranking and selection,” in Proc. Winter Simulation Conf., Phoenix, AZ,
2011, pp. 4319–4331.
[18] S. S. Gupta, “On a decision rule for a problem in ranking means,” Ph.D. dissertation, Dept. Stat., North Carolina Univ., Chapel Hill, North Carolina, 1956.
[19] A. Geoffrion, J. Dyer and A. Feinberg, “An interactive approach for multi-criterion optimization with an application to the operation of an academic department,” Manage. Sci., vol. 19, no. 4, pp. 357–368, 1972.
[20] G. Guill’en, F. D. Mele, M. J. Bagajewicz, A. Espuna and L. Puigjaner, “Multiobjective supply chain design under uncertainty,” Chem. Eng. Sci., vol. 60, no. 6, pp. 1535–553, 2005.
[21] F. Hnaien, X. Delorme and A. Dolgui, “Multi-objective optimization for inventory control in two-level assembly systems under uncertainty of lead times,” Comput. Oper. Res., vol. 37, no. 11, pp. 1835–1843, 2010.
[22] H. C. Zhou, G. H. Zhang, and G. L. Wang, “Multi-objective decision making approach based on entropy weights for reservoir flood control operation [J],” J. Hydraul. Eng. vol. 38, pp. 100–106, no. 1, 2007.
[23] J. S. Hammond, R. L. Keeney and H. Raiffa, “Even swaps: a rational method for making trade-offs,” Harv. Bus. Rev., vol. 76, no. 2, pp. 137–149, 1998.
[24] R. A. Halim and M. D. Seck, “The simulation-based multi-objective evolutionary
optimization framework,” in Proc. Winter Simulation Conf., Phoenix, AZ, 2011, pp. 2839–2851.
[25] L. J. Hong and B. L. Nelson, “Discrete optimization via simulation using COMPASS,” Oper. Res., vol. 54, no. 1, pp. 115–129, 2006.
[26] J. A. Joines, D. Gupta, M. A. Gokce, R. E. King and M. G. Kay, “Supply chain multiobjective simulation optimization,” in Proc. Winter Simulation Conf., San Diego, California, 2002, pp. 1306–1313.
[27] R. B. Kazemzadeh, M. Bashiri, A. C. Atkinson and R. Noorossana, “A general framework for multiresponse optimization problem based on goal programming,”
Eur. J. Oper. Res., vol. 189, no. 2, pp. 421–429, 2008.
[28] S. H. Kim and B. L. Nelson, “A fully sequential procedure for indifference-zone selection in simulation,” ACM Trans. Model. Comput. Simul., vol. 11, no. 3, pp.
251–273, 2001.
[29] M. M. K¨oksalan and P. N. S. Sagala, “Interactive approaches for discrete alternative multiple criteria decision making with monotone utility functions,” Manage. Sci., vol. 41, no. 7, pp. 1158–1171, 1995.
[30] D. H. Lee, K. J. Kim and M. K¨oksalan, “An interactive method to response surface optimization based on pairwise comparisons,” IIE Trans., vol. 44, no. 1, pp. 13–26, 2012.
[31] L. H. Lee, E. P. Chew, S. Y. Teng and Y. K. Chen, “Multi-objective simulation-based evolutionary algorithm for an aircraft spare parts allocation problem,” Eur. J. Oper.Res., vol. 189, no. 2, pp. 476–491, 2008.
[32] L. H. Lee, C. Lee and Y. P. Tan, “A multi-objective genetic algorithm for robust flight scheduling using simulation,” Eur. J. Oper. Res., vol. 177, no. 3, pp. 1948–
1968, 2007.
[33] L. H. Lee, S. Y. Teng, E. P. Chew, K. W. Lye and P. Lendermann, “Application of multi-objective simulation optimization techniques to inventory managenent proplems,” in Proc. Winter Simulation Conf., Piscataway, New Jersey, 2005, pp. 1684–1691.
[34] R. T. Marler and J. S. Arora, “Survey of multi-objective optimization methods for engineering,” Struct. Multidiscip. Optim., vol. 26, no. 6, pp. 369–395, 2004.
[35] A. Mirzazadeh, “Inventory management under stochastic conditions with multiple objectives,” Artif. Intell. Res., vol. 2, no. 3, pp. 16–26, 2013.
[36] B. L. Nelson, J. Swann, D. Goldsman andW. Song, “Simple procedure for selection the best simulated system when the number of alternative is large,” Oper. Res., vol. 49, no. 6, pp. 950–963, 2001.
[37] Y. O¨ zgu¨r and G. M. Bayhen, “Modelling and optimization of average travel time for a metro line by simulation and response surface methodology,” Eur. J. Oper. Res., vol. 196, no. 1, pp. 225–233, 2009.
[38] A. Persson, H. Grimm, Ng. Amos, T. Lezama, J. Ekberg, S. Falk and P. Stablum, “Simulation-based multi-objective optimization of a realworld scheduling problem,” in Proc. Winter Simulation Conf., Monterey, CA, 2006, pp. 1757–1764.
[39] S. PrasannaVenkatesan and S. Kumanan, “Multi-objective supply chain sourcing strategy design under risk using PSO and simulation,” Int. J. Adv. Manuf. Tech., vol.
61, no. 1-4, pp. 325–337, 2012.
[40] C. E. Riddalls, S. Bennett and N. S. Tipi, “Modelling the dynamics of supply chains,” Int. J. Syst. Sci., vol. 31, no. 8, pp. 969–976, 2000.
[41] J. Pichitlamken, B. L. Nelson and L. J. Hong, “A sequential procedure for neighborhood selection-of-the-best in optimization via simulation,” Eur. J. Oper. Res., vol. 173, no. 1, pp. 283–298, 2006.
[42] S. L. Rosen, C. M. Harmonosky and M. T. Traband, “Optimization of systems with multiple performance measures via simulation: Survey and recommendations,” Comput. Ind. Eng., vol. 54, no. 2, pp. 327–339, 2008.
[43] J. Ryu, S. Kim and H. Wan , “Pareto front approximation with adaptive weighted sum method in multiobjective simulation optimization,” in Proc. Winter Simulation
Conf., Piscataway, NJ, 2009, pp. 623–633.
[44] Y. Rinott, “On two-stage selection procedures and related probability-inequalities,” Commun. Stat. - Theory Methods., vol. 7, no. 8, pp. 799–811, 1978.
[45] R. Sakiani, S. M. T. Fatemi Ghomi and M. Zandieh, “Multi-objective supply planning for two-level assembly systems with stochastic lead times,” Comput. Oper. Res., vol. 39, no. 7, pp. 1325–1332, 2012.
[46] A. Syberfeldt, A. Ng, R. I. John and P. Moore, “Multi-objective evolutionary simulation-optimisation of a real-world manufacturing problem,” Robot. Comput.-
Integr. Manuf., vol. 25, no. 6, pp. 926–931, 2009.
[47] C. S. Tsou, “Multi-objective inventory planning using MOPSO and TOPSIS,” Expert Syst. Appl., vol. 35, no. 1, pp. 136–142, 2008.
[48] F. Tricoire, A. Graf and W.J. Gutjahr, “The bi-objective stochastic covering tour problem,” Comput. Oper. Res., vol. 39, no. 7, pp. 1582–1592, 2012.
[49] C. S. Tsou, “Evolutionary Pareto optimizers for continuous review stochastic inventory system,” Eur. J. Oper. Res., vol. 195, no. 2 (2009) 364–371.
[50] F. Wang, X. Lai and N. Shi, “A multi-objective optimization for green supply chain network design,” Decis. Support Syst., vol. 51, no. 2, pp. 262–269, 2011.
[51] D. Wu and D. L Olson, “Supply chain risk,simulation and vendor selection.” Int. J. Prod. Econ., vol. 114, no. 2, pp. 646–655, 2008.
[52] Y. Wang, K. L. Luangkeson and L. J. Shuman, “A fully sequential best subset selection procedure,” Working Paper, 2014.
[53] H. Zhang, “Multi-objective simulation-optimization for earthmoving operations,” Automat. Constr., vol. 18, no. 1, pp. 79–86, 2008.