本論文針對一個將需求區分為多等級的庫存配給問題下，探討如何維持庫存數量來滿足各式各樣的需求。當倉庫的庫存有限時，我們傾向將庫存提供給等級較高的需求，而為了處理在供貨前置時間內所存在之不確定性因子，我們提出了兩個方法對每一個來到的顧客進行滿足與否其需求之判斷，此兩個方法分別是動態隨機庫存配給決策步驟(dynamic stochastic inventory rationing decision procedure)以及風險水準庫存配給決策步驟(risk level inventory rationing decision procedure)。此庫存配給問題的目標為在滿足任何等級較低的需求前，儘可能將庫存優先提供給等級較高的需求，同時在供貨到達前，我們也希望有能力來滿足等級較低的需求以避免庫存殘留的情況發生。根據模擬實驗的結果可知，風險水準庫存配給決策步驟較其他方法能最有效地提升最高等級需求的滿足率，而動態隨機庫存配給決策步驟可在維持最高等級需求的滿足率下，同時也能提升最高等級需求的滿足率。此外，有別於其他研究，本論文更能處理需求數量以及供貨前置時間為隨機變數之存貨系統，甚至在需求數量以及供貨前置時間為固定參數之存貨系統下，本論文提出之方法之績效也優於其他研究。

This study considers an inventory rationing problem which maintains inventory to meet various requests of a discrete number of priority classes. When there is limited available quantity in the warehouse, we prefer to fulfill the higher priority requests than lower priority requests. To face the uncertain factors during replenishment lead time, we develop two rationing approaches, called dynamic stochastic inventory rationing decision procedure (DSIR) and risk level inventory rationing decision procedure (RLIR), to determine whether to fulfill the request of each arrival customer. The objective of the problem is to provide inventory to higher priority requests before any lower priority requests. Also, we would rather satisfying lower priority request than having inventory leftover when the replenishment arrives. The simulation experiments show that RLIR maintains high fill rate of the first priority request more aggressive than other approaches. Whereas, DSIR maintains a good fill rate of first priority requests, while keeping a high overall fill rate. Furthermore, unlike previous studies, the proposed approaches can handle inventory systems with random request quantity and random replenishment lead time. Even under the case of constant request quantity and constant lead time, the performance of proposed approaches is better than previous approach.

Ayanso, A. and Diaby, M. and Nair, S.K. “Inventory rationing via drop-shipping in Internet retailing”, European Journal of Operational Research, Vol. 171, pp.135-152.
Cohen, M.A. and Kleindorfer, P.R. and Lee, L. (1998), “Service constrained (s,S) inventory systems with priority demand classes and lost sales”, Management Science, Vol. 28, pp.1296-1303.
Deshpande, V. and Cohen, A.M. and Donohue, K. (2003), “A Threshold Inventory Rationing Policy for Service-Differentiated”, Management Science, Vol. 49, No. 6, pp.683-703.
Ha, A.Y. (1997), “Inventory rationing in a make-to-stock production system with several demand classes and lost sales”, Management Science, Vol. 43, No. 8, pp.1093–1103.
Haynsworth, H.C. and Price, B.A. (1989), “A model for use in the rationing of inventory during lead time”, Naval Research Logistics, Vol. 36, No. 4, pp.491-506.
Hung, Y.F. and Lee, T.Y. (2007), “Capacity Rationing Decision Procedures with Order Profit as a Continuous Random Variable”, unpublished paper, Department of Industrial Engineering and Engineering management, National TsingHua University.
Kaplan, S. (1969), “Stock rationing”, Management Science, Vol. 15, No. 5, pp.260-267.
Moon, I. and Kang, S. (1998), “Rationing Policies for Some Inventory Systems”, The Journal of the Operational Research Society, Vol. 49, No. 5, pp.509-518.
Nahmias, S. and Demmy, W.S. (1981), “Operating characteristics of an inventory system with rationing”, Management Science, Vol. 27, No. 11, pp.1236-1245.
Topkis, D.M. (1968), “Optimal ordering and rationing policies in a non-stationary dynamic inventory model with n demand classes”, Management Science, Vol. 15, pp.160-176.
Veinott, A.F (1965), “Optimal policy in a dynamic, single product, non-stationary inventory model with several demand classes”, Operation Research, Vol. 13, pp. 761-778.