隨機產能配給決策方法之延伸

Extensions from Stochastic Capacity Rationing Decision Approach

蔡秉亨(Ping-Heng Tsai)

指導教授 ： 洪一峯

國立清華大學/工學院/工業工程與工程管理學系/碩士(2008年)

https://doi.org/10.6843/NTHU.2008.00387

摘要

當一個接單式系統(make-to-order)的製造商面臨期望總需求大於現有產能的情況下，Hung and Lee (2007) 提出一個可以有效地解決此類的隨機性訂單選擇問題的決策過程，叫做動態隨機產能配給過程(dynamic stochastic capacity rationing procedure, briefly DSCR)。但和先前的研究有很大的不同，他們的方法不需要將產品依照利潤分等級，此外，把一筆訂單的利潤和產能需求量假設為連續型的隨機變數。本篇研究將延伸Hung and Lee (2007)提出的決策模型，使其方法能應用到不同的真實環境裡。
(1)在Hung and Lee (2007)原本的方法裡沒有標準的產品，也就是說將產品分類是不可能的。在本研究的第一個延伸，我們假設產品可以被分成數個間斷型的利潤等級。在這樣的假設下，本研究將修改DSCR法並與先前已提出的方法做比較。
(2)在大部分製造業的工廠，顧客經常會被詢問需要的產品數量和要求的交貨日期，然而，工廠的業務員會回應給顧客訂單的價格和達交的日期，在這樣的營運流程下，價格(或利潤)對決策者而言往往是一個未知數；換言之，決策者必須自己決定訂單的價格(或利潤)。在延伸二中，我們提供一個工具幫助決策者報價給顧客。
(3)一些製造業的交易允許部分訂單的滿足，在這樣的條件下，我們應該如何決定部分訂單該滿足的量就是我們延伸三的焦點。

關鍵字

需求管理 ； 產能配給 ； 決策分析

並列摘要

When the expected demands of a make-to-order manufacturer exceeds its available capacity, a decision procedure, called dynamic stochastic capacity rationing procedure (DSCR), proposed by Hung and Lee (2007) can effectively solve such a stochastic order selection problem. Unlike previous studies, their approach does not need to classify product by profit; furthermore, the profit and capacity requirement of a random order are assumed as continuous random numbers. This study makes three extensions from original approach by Hung and Lee (2007) in order to make the decision procedure more applicable in actual practices.
(1) In Hung and Lee’s original problems, there is no standard product; i.e., classification is impossible. In the first extension of this study, we assume the products can be classified into a discrete number profit classes. Under such an assumption, various approaches proposed previously are applicable and, in this study, are used to compare with the modified DSCR.
(2) In many manufacturing firms, the inquiry issued by a customer includes the request quantity and request delivery date. Then, a sale person of the manufacturing firm replies with a quotation that includes an asking price and a confirmed delivery date. Under such a business process scenario, the price (or, profit) is not a given parameter to the decision maker. Instead, the decision maker should determine the price (or, profit). The second extension of this study provides an aiding tool for the decision maker to determine the quotation prices of the customer inquiry.
(3) Some manufacturing business allow partial order fulfillment. Under such a condition, how we determine the quantity of the fulfilled partial order in order to maximize the expected profit is the focus of the third extension.

並列關鍵字

Demand management ； Capacity rationing ； Decision analysis

參考文獻

Badinelli, R.D., An optimal, dynamic policy for hotel yield management. European Journal of Operational Research, 2000, 121 (3), 476-503.

Balakrishnan, N., Patterson, J.W. and Sridharan, V., Robustness of capacity rationing policies. European Journal of Operational Research, 1999, 115 (2), 328-338.

Balakrishnan, N., Sridharan, V. and Patterson, J.W., Rationing capacity between two product classes. Decision Sciences, 1996, 27 (2), 185-214.

Barut, M. and Sridharan, V., Design and evaluation of a dynamic capacity apportionment procedure. European Journal of Operational Research, 2004, 155 (1), 112-133.

Barut, M. and Sridharan, V., Revenue management in order-driven production systems. Decision Sciences, 2005, 36 (2), 287-316.