(18.210.12.229) 您好!臺灣時間:2021/02/26 08:56
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:藍俊宏
研究生(外文):ChunHung Lan
論文名稱:聚合、預測與解析之需求規劃策略分析研究
論文名稱(外文):Performance Analysis of Demand Planning Approaches for Aggregating, Forecasting and Disaggregating Interrelated Demands
指導教授:陳正剛陳正剛引用關係
指導教授(外文):Argon Chen
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:工業工程學研究所
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:英文
論文頁數:84
中文關鍵詞:需求規劃
外文關鍵詞:Demand Planning
相關次數:
  • 被引用被引用:3
  • 點閱點閱:211
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
需求規劃為供應鏈規劃之前端,因此需求規劃結果的品質對於整個供應鏈營運的效率有很大的影響。然而需求資訊往往在供應鏈網路的層層傳遞過程中,嚴重地扭曲,造成需求變異大幅擴張,使得整個供應鏈規劃的品質嚴重的降低。為了應付全球化市場上的供給與需求,製造業者不得不正視需求規劃的重要性。
在現行的需求規劃方法中,透過聚合、統計預測等策略的使用來降低需求變異,是提升需求規劃準確性的有效方法。在本研究中,我們著眼於聚合需求以進行統計預測,再行解析回個別預測值的需求規劃策略。我們利用以二元自我迴歸時間序列模型模擬兩筆相關的需求數列進行分析。本研究發現,聚合進行統計預測後,再行解析至個別預測值的需求規劃策略在大多數的情形下都得不到有效的結果,只有在以下情形吻合時,此策略方可採用:
(1)需求資料的可預測趨勢相近;
(2)需求資料間的正相關性越強;
(3)兩原始需求資料的變異係數相近,且解析後需求數列之變異係數小於原始需求資料的變異係數。
Results of demand planning serve as the basis of every planning activity in a demand-supply network and ultimately determine the effectiveness of manufacturing and logistic operations in the network. The uncertainty of demand signals, that are propagated and magnified over the network, becomes the crucial cause of ineffective operation plans.
To manage the demand variability, appropriate demand aggregation and statistical forecasting approaches are known to be effective. In this research, we focus on a common demand planning approach where an aggregated demand is first forecasted and then disaggregated to forecasts for individual demands. The bivariate VAR(1) time series model will be used to simulate two interrelated demands. A very important finding of our research is that disaggregation of a forecasted aggregated demand is not effective in most cases and should be employed only when
1.predictable trends of two demands are similar;
2.correlation of two demands is positive and strong;
3.the two original CV’s are close and the CV’s after disaggregation are smaller than original CV’s.
Abstract i
論文摘要 ii
Contents iii
Contents of Figures vi
Contents of Tables ix
Chapter 1: Introduction 1
1.1 Background & Motivations 1
1.2 Problem Description & Research Objective 2
1.3 Thesis Structure 4
Chapter 2: Literature Review 5
2.1 Time Series Analysis 5
2.1.1 Box-Jenkins Time Series Models 6
2.1.2 Forecasting for Time Series Models 7
2.2 Demand Aggregation and Forecasting Approaches 9
2.2.1 Defining Demand Planning Approaches 9
2.2.2 Performance Analysis of Demand Planning Approaches 10
2.2.3 Evaluation and Conclusions 13
2.3 Disaggregating Methodologies 16
Chapter 3: Demand Modeling and Planning Approaches 17
3.1 VAR(1) Demand Model 17
3.2 Demand Planning Approaches 19
3.3 Forecasting Performances of Demand Planning Approaches 20
3.3.1 Forecasting MSE of Approach 1 and 2 22
3.3.2 Forecasting MSE of Approach 3 22
3.3.4 Forecasting MSE of Approach 4 23
3.3.5 Forecasting MSE of Approach 5 24
3.4 Performance Index 25
Chapter 4: Evaluation of Demand Planning Approaches 26
4.1 Design of Evaluation Methods and Scenarios 26
4.2 Performance Analysis of Approaches 1 and 2 28
4.3 Performance Analysis of Approaches 3 30
4.4 Performance Analysis of Approaches 4 32
4.4.1 Performance Analysis for Scenario 1 41
4.4.2 Performance Analysis for Scenario 5 44
4.4.3 Performance Analysis for Scenario 6 46
4.4.4 Performance Analysis for Scenario 9 49
4.4.5 Performance Analysis for Scenario 13 51
4.4.6 Summary of Effects on Performance 53
4.5 Comparisons among Demand Planning Approaches 54
Chapter 5: Evaluating Scenario 58
Chapter 6: Conclusions and Remarks 62
6.1 Rules and Principles 62
6.2 Remarks 63
Reference 64
Appendix A: Deductions of Forecasting Error 65
A.1 Deductions of MLE and MSE in Approach 3 65
A.2 Deductions of MLE and MSE in Approach 4 66
A.3 MSE of Lag l in Approach 5 68
Appendix B: Proof of Theorem 1 70
Appendix C: Performance Analysis for Unmentioned Scenarios 71
C.1 Performance Analysis for Scenario 2 71
C.2 Performance Analysis for Scenario 3 72
C.3 Performance Analysis for Scenario 4 74
C.4 Performance Analysis for Scenario 7 75
C.5 Performance Analysis for Scenario 8 77
C.6 Performance Analysis for Scenario 10 78
C.7 Performance Analysis for Scenario 11 80
C.8 Performance Analysis for Scenario 12 81
C.9 Performance Analysis for Scenario 14 83
[1] Lee, H. L., V. Padmanabhan, and S. Whang, “The bullwhip effect in supply chains”, Sloan Management Review, Spring, 1997.
[2] Charles W. Gross, Jeffrey E. Sohl, “Disaggregation methods to expedite product line forecasting”, Journal of Forecasting, Vol. 9, pp 233-254, 1990.
[3] 葉小蓁, “時間數列分析與應用”, 1998.
[4] William W. S. Wei, “Time series analysis: univariate and multivariate methods”, 1994.
[5] 徐佳豪, “需求之聚合預測策略研究”, 國立台灣大學工業工程學研究所碩士班論文, 2001.
[6] George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, “Time Series Analysis Forecasting and Control” 3rd edition, 1994.
[7] C. W. J. Granger, M. J. Morris, “Time series modeling and interpretation”, Journal of the Royal Statistical Society — Series A, Vol. 139, pp 246-257, 1976.
[8] Averill M. Law, W. David Kelton, “Simulation modeling and analysis”, 2nd edition, 1991.
[9] Richard A. Johnson, Dean W. Wichern, “Applied multivariate statistical analysis”, 4th edition, 1998.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔