本研究將依據朱(2009)所探討的考慮需求不確定之單階層多廠區隨機產能規劃問題，以及延伸吳(2011)所提出的模擬為基之近似動態規劃，建構即時近似動態規劃模型(Real-Time Approximate Dynamic Programming Algorithm)，在TFT-LCD產業面臨市場需求具有劇烈波動的環境中，考量在規劃期間內，各產品族於各期具有不同的需求分配，且前後期的需求間存在相依性，在欲達到利潤最大的目標下，決定各期各產品族之最佳產能分配決策，以及當現有產能無法滿足時，決定最佳產能擴充決策，透過購買各產品之專屬附屬設備－光罩，以增加產品族於各廠區之產能。
本研究使用k-Nearest Neighbor Approximation之方法與Rolling Horizon的概念修正近似動態規劃在隨機模擬過程中被忽略狀態的衡量方式，提出了k-NN為基之近似動態規劃(k-Nearest-Neighbor based Approximate Dynamic Programming)與滾動為基之近似動態規劃(Rolling-Horizon based Approximate Dynamic Programming)，以縮小狀態與決策空間，在提升運算效率之前提下，達到即時決策之目的，以期能更有效率地得到最佳產能分配結果與更穩健的產能擴充計畫。
本研究將使用與朱(2009)相同的產業實例，驗證所提出的即時近似動態規劃模式，並與朱(2009)建構的隨機動態規劃模式結果進行比較，利用蒙地卡羅模擬法，隨機抽樣各期各產品族的需求分配，以驗證此即時近似隨機動態規劃模式的可行性與有效性，實驗證實，本研究之方法不但可找到與隨機動態規劃極微相似的最佳產能擴充路徑，且大幅減少衡量的狀態與決策空間，有效縮短運算時間。此外，本研究也探討在問題特性下，Heuristics與問題數據之參數設定對於求解結果之影響，以評估模型的適用環境。最後，將本研究模型應用至Large Scale的問題上，在隨機動態規劃已無法於有限時間內求解的問題中，評估本研究之模型的求解效率，實驗結果得知，本研究之模型仍然可在有限的時間內求得一組近似最佳的產能擴充解。從以上實驗證實，本研究提出之即時近似動態規劃模型可達到節省運算資源與即時決策之兩大目的。

1.陳韋均，「TFT Array多廠區之產能與產品組合規劃問題」，國立清華大學工業工程與工程管理學系碩士論文，2006。
2.陳子立、林則孟，2008，「需求不確定下之TFT-LCD多廠區隨機產能規劃模式」， 九十七年度中國工業工程學會年會論文，中原大學。
3.張益菁，「考慮需求不確定之單階多廠產能規劃問題-以TFT-LCD產業為例」，國立清華大學工業工程與工程管理學系碩士論文，2007。
4.示欣惠，「二階層多廠區產能規劃—以TFT-LCD產業為例」，國立清華大學工業工程與工程管理學系碩士論文，2008。
5.楊宗翰，「考量需求與價格相關之隨機動態產能規劃—以TFT-LCD產業為例」，國立清華大學工業工程與工程管理學系碩士論文，2008。
6.朱曉晴，「考量需求不確定性之隨機動態產能規劃—以TFT-LCD產業為例」，國立清華大學工業工程與工程管理學系碩士論文，2009。
7.吳蘇容，「模擬為基之近似動態規劃應用在TFT-LCD產能規劃問題」，國立清華大學工業工程與工程管理學系碩士論文，2011。
8.Bhatnager, S., Gaucherand, E. F., Fu, M. C., He, Y. and Marcus, S. I., “A Markov Decision Process Model for Capacity Expansion and Allocation”, Proceedings of the 38th Conference on Decision & Control, pp.1380-1385, 1999.
9.Ceryan, O. and Koren, Y., “Manufacturing Capacity Planning Strategies”, CIRP Annals - Manufacturing Technology, Vol.58(1), pp.403-406, 2009.
10.Chen, T. L., Lin, J. T. and Fang, S. C., “A Shadow-Price Based Heuristic for Capacity Planning of TFT-LCD Manufacturing”, Journal of Industrial and Management Optimization, 6, pp.209-239, 2010.
11.Cheng, L., Subrahmanian, E. and Westerberg, W., “Multi-objective decisions on capacity planning and production-inventory control under uncertainty”, Industrial & Engineering Chemistry Research, 43, pp.2192-2208, 2004.
12.Choi, J., Realff, M. J. and Lee, J. H., “Dynamic Programming in A Heuristically Confined State Space: A Stochastic Resource-Constrained Project Scheduling Application”, Computers & Chemical Engineering, Vol.28, pp.1039-1058, 2004.
13.Choi, J., Lee, J. H. and Realff, M. J., “An Algorithm Framework for Improving Heuristic Solutions Part II: A New Version of the Stochastic Traveling Salesman Problem”, Computers & Chemical Engineering, Vol.28(8), pp.1297-1307, 2004.
14.Choi, J., Realef, M. J. and Lee, J. H., “Stochastic Dynamic Programming with Localized Cost-to-go Approximators Application to Large Scale Supply Chain Management under Demand Uncertainty”, Chemical Engineering Research and Design, 83(A6), pp.752-758, 2005.
15.Choi, J., Realff, M. J. and Lee, J. H., “Approximate Dynamic Programming: Application to Process Supply Chain Management”, AIChE Journal, Vol.52, No.7, pp.2473-2485, 2006.
16.Hood, S. J., Bermon, S. and Barahona, F., “Capacity Planning under Demand Uncertainty for Semiconductor Manufacturing“, IEEE Transactions on Semiconductor Manufacturing, 16(2), pp.173-280, 2003.
17.Katanyukul, T., Duff, W. S. and Chong, E. K. P., “Approximate Dynamic Programming for An Inventory Problem: Empirical Comparison”, Computers & Industrial Engineering, in press, 2011.
18.Li, C., Liu, F., Cao, H. and Wang, Q., “A Stochastic Dynamic Programming Based Model for Uncertain Production Planning of Re-manufacturing System”, International Journal of Production Research, 47(13), 3657-3668, 2009.
19.Lin, J. T., Chen, T. L. and Lin, Y. T., “A Hierarchical Planning and Scheduling Framework for TFT-LCD Production Chain”, 2006 IEEE International Conference on Service Operations and Logistics, and Informatics, pp.711-716, 2006.
20.Lin, J. T., Chen, T. L. and Chen, W. J., “Capacity and product mix planning problem for TFT Array multi-plant”, Journal of the Chinese Institute of Industrial Engineers, 24(6), pp.489-504, 2007.
21.Lin, J. T., Wu, C. H., Chen, T. L. and Shih, S. H., “A Stochastic Programming Model for Strategic Capacity Planning in Thin Film Transistor – Liquid Crystal Display (TFT-LCD) Industry”, Computers & Operations Research, 38(7), pp.992-1007, 2010.
22.Lin, J. T., Chen, T. L.and Chu, H. C., “A Stochastic Dynamic Programming Approach for Multi-Site Capacity Planning in TFT-LCD Manufacturing under Demand Uncertainty”, working paper, under review, 2012.
23.Pratikakis, N.E., Realff, M. J. and Lee, J. H., “A Real Time Adaptive Dynamic Programming Approach For Planning and Scheduling”, Computer Aided Chemical Engineering, Vol. 21, pp.1179-1184, 2006.
24.Pratikakis, N.E., Realff, M. J. And Lee, J. H., “Accounting Risk in Multistage Stochastic Problems Using Approximate Dynamic Programming”, 8th International IFAC Symposium on Dynamics and Control of Process Systems, pp.153-158, 2007.
25.Pratikakis, N.E., “Multistage Decisions and Risk in Markov Decision Processes : Towards Effective Approximate Dynamic Programming Architectures”, Georgia Institute of Technology, 2008.
26.Pratikakis, N.E., Realff, M. J. and Lee, J. H., “Strategic Capacity Decision-Making in A Stochastic Manufacturing Environment Using Real-Time Approximate Dynamic Programming”, Naval Research Logistics, Vol.57 (3), pp. 211–224, 2010.
27.Rajagopalan, S., Singh, M. R. and Morton, T. E., “Capacity Expansion and Replacement in Growing Markets with Uncertain Technological Breakthroughs”, Management Science, 44(1), pp.12-30, 1998.
28.Sutton, R. S. and Barto, A. G., Reinforcement Learning, 3rd edition, (The MIT Press, Cambridge, Massachusetts, USA).
29.Wu, C. H. and Chuang, Y. T., “An innovative Approach for Strategic Capacity Portfolio Planning under Uncertainties”, European Journal of Operational Research, 207(2), pp.1002-1013, 2010.