This research introduces a general approach for integrating a probabilistic model of the changes in the committed orders with an analytical model of production and inventory planning under multi-period Quantity Flexibility contracts. We study a decentralized structure where a capacitated manufacturer, capable of subcontracting, serves multiple contract buyers who actually perform forecasts on a rolling horizon basis. We model the evolution of buyers' / commitments as a multiplicative forecast evolution process accommodating contract revision limits. A finite Markovian approximation to this sophisticated evolution model is introduced for facilitating the associated complex probability modeling. We implement computational dynamic programming and introduce an effective approach for reducing state-space dimensionality building upon our forecast evolution structure. Computational investigation demonstrates how the manufacturer benefits from the existence of order commitments and subcontracting option by analyzing the interplay of decisions.
Identifer | oai:union.ndltd.org:METU/oai:etd.lib.metu.edu.tr:http://etd.lib.metu.edu.tr/upload/12609902/index.pdf |
Date | 01 September 2008 |
Creators | Kayhan, Mehmet |
Contributors | Kayaligil, Sinan |
Publisher | METU |
Source Sets | Middle East Technical Univ. |
Language | English |
Detected Language | English |
Type | Ph.D. Thesis |
Format | text/pdf |
Rights | To liberate the content for public access |
Page generated in 0.0018 seconds