由於氣候變遷，台灣的極端降雨事件日益頻繁，嚴重的洪水破壞已成為一個緊迫的問題，然而現有的防洪基礎建設可能不足以應對未來的極端降雨， 因此本研究製定每年安排防洪基礎設施的策略，並分成兩個目標，分別是最小化長期總災害損失、最小化長期平均災害損失比例。
本研究以台南市三爺溪流域進行個案探討，考慮了一系列的防洪基礎建設，其中包括流量分洪入海、流量分洪入二仁溪、增設滯洪池於三爺溪上游、增設滯洪池於三爺溪下游、堤防增高、河道拓寬、下水道導流，也考慮各種限制包含每年防洪基礎建設的建設成本和維護成本總和不超出預算、防洪基礎建設的建設次數不可超過上限、每次防洪基礎建設量不可超過上限、防洪基礎建設總量不可超過上限、防洪基礎建設的建設期間不可規劃該建設。為了找出最佳的防洪基礎設施規劃方案以最小化長期總災害損失、最小化長期平均災害損失比例，本研究建立了一個新的啟發式演算法—改進的自適應基於教學最佳化演算法，在每次迭代中改變防洪基礎建設規劃的資源配置和排程。

Due to climate change, extreme rainfall events in Taiwan are becoming increasingly frequent, leading to severe flood damage, which has become an urgent issue. However, the existing flood control infrastructure may not be sufficient to cope with future extreme rainfall. The purpose of this study is to develop strategies for the annual deployment of flood control infrastructure, with two objectives: minimizing long-term total disaster cost and minimizing the long-term average disaster cost ratio.
This study conducts a case analysis of the Sanye Creek basin in Tainan City, considering a range of flood control infrastructure options, including diverting flow to the sea, diverting flow to the Erren River, adding detention ponds upstream of Sanye Creek, adding detention ponds downstream of Sanye Creek, raising dikes, widening river channels, and enhancing sewer diversion. Various constraints are also considered, such as ensuring that the total annual construction and maintenance costs of flood control infrastructure do not exceed the budget, the number of flood control infrastructure constructions does not exceed the upper limit, and the construction period of flood control infrastructure does not overlap, among others.
To identify the optimal flood control infrastructure planning scheme that minimizes long-term total disaster cost and the long-term average disaster cost ratio, this study develops a novel heuristic algorithm—an improved adaptive Teaching-Learning-Based Optimization algorithm, which adjusts the resource allocation and scheduling of flood control infrastructure planning in each iteration.

致謝 I
摘要 II
Abstract III
目錄 IV
圖目錄 VI
表目錄 VII
第一章　緒論 1
1.1研究背景與動機 1
1.2研究目的 2
1.3論文架構 3
第二章　文獻回顧 5
2.1防洪基礎建設策略規劃 5
2.2 多階段隨機規劃模型 10
2.3最佳化求解方法 13
第三章　數學模型 18
3.1 符號定義 18
3.2 問題定義 20
3.2.1 防洪基礎建設每年可用量 21
3.2.2 防洪基礎建設建造規則 22
3.3 規劃防洪基礎建設策略的數學模型一 24
3.3.1 年度災害損失函數 24
3.3.2 多階段隨機規劃模型 27
3.4 規劃防洪基礎建設策略的數學模型二 29
第四章　求解方法 32
4.1基於教學最佳化演算法 33
4.2自適應基於教學最佳化演算法 36
4.3改進的自適應基於教學最佳化演算法 40
第五章 個案分析 50
5.1實驗區域 50
5.2數學模型一的模擬模型 52
5.2.1日降雨量生成 52
5.2.2估計長期災害損失 54
5.2.3 各演算法的比較 57
5.2.4 敏感度分析 58
5.3數學模型二的模擬模型 64
5.3.1估計長期災害損失比例 64
5.3.2 各演算法的比較 66
5.3.3 敏感度分析 67
5.4防洪基礎建設規劃分析 71
第六章　結論與未來展望 73
參考文獻 74

Abdel-Basset, M., Abdel-Fatah, L., & Sangaiah, A. K. (2018). Metaheuristic algorithms: A comprehensive review. Computational intelligence for multimedia big data on the cloud with engineering applications, 185-231.
Bakker, H., Dunke, F., & Nickel, S. (2020). A structuring review on multi-stage optimization under uncertainty: Aligning concepts from theory and practice. Omega, 96, 102080.
Barah, M., Khojandi, A., Li, X., Hathaway, J., & Omitaomu, O. (2021). Optimizing green infrastructure placement under precipitation uncertainty. Omega, 100, 102196.
Birge , JR & Louveaux , F . 1997 . Introduction to stochastic programming , New York : Springer .
Brekelmans, R., Hertog, D. D., Roos, K., & Eijgenraam, C. (2012). Safe dike heights at minimal costs: The nonhomogeneous case. Operations research, 60(6), 1342-1355.
Degertekin, S. O., & Hayalioglu, M. S. (2013). Sizing truss structures using teaching-learning-based optimization. Computers & Structures, 119, 177-188.
Dlamini, N. S., Rowshon, M. K., Sahab, U., Fikri, A., Lai, S. H., & Mohd, M. S. F. (2015). Developing and calibrating a stochastic rainfall generator model for simulating daily rainfall by Markov chain approach. Jurnal Teknologi, 76(15).
El-Arini, M., & Fathy, A. (2015). An Efficient and reliable method for optimal allocating of the distributed generation based on optimal teaching learning algorithm. WSEAS Transactions on Power Systems, 10.
Fang, Y., Chen, L., & Fukushima, M. (2008). A mixed R&D projects and securities portfolio selection model. European Journal of Operational Research, 185(2), 700-715.
Kall , P & Mayer , J . (2005). Stochastic linear programming , Springer's International Series. New York : Springer .
Kall , P & Wallace , SW . (1994). Stochastic programming , New York : John Wiley & Sons .
Kazemi Zanjani, M., Nourelfath, M., & Ait-Kadi, D. (2010). A multi-stage stochastic programming approach for production planning with uncertainty in the quality of raw materials and demand. International Journal of Production Research, 48(16), 4701-4723.
Li, Y. P., Huang, G. H., Nie, S. L., & Liu, L. (2008). Inexact multistage stochastic integer programming for water resources management under uncertainty. Journal of Environmental Management, 88(1), 93-107.
Postek, K., Den Hertog, D., Kind, J., & Pustjens, C. (2019). Adjustable robust strategies for flood protection. Omega, 82, 142-154.
Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2011). Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems. Computer-aided design, 43(3), 303-315.
Roy, P. K. (2013). Teaching learning based optimization for short-term hydrothermal scheduling problem considering valve point effect and prohibited discharge constraint. International Journal of Electrical Power & Energy Systems, 53, 10-19.
Song, H., & Huang, H. C. (2008). A successive convex approximation method for multistage workforce capacity planning problem with turnover. European Journal of Operational Research, 188(1), 29-48.
Triki, C., Beraldi, P., & Gross, G. (2005). Optimal capacity allocation in multi-auction electricity markets under uncertainty. Computers & operations research, 32(2), 201-217.
Xu, H., Ma, C., Xu, K., Lian, J., & Long, Y. (2020). Staged optimization of urban drainage systems considering climate change and hydrological model uncertainty. Journal of Hydrology, 587, 124959.
Zhou, Y., Huang, G. H., & Yang, B. (2013). Water resources management under multi-parameter interactions: A factorial multi-stage stochastic programming approach. Omega, 41(3), 559-573.
Zou, F., Chen, D., & Xu, Q. (2019). A survey of teaching–learning-based optimization. Neurocomputing, 335, 366-383.
Zwaneveld, P., Verweij, G., & van Hoesel, S. (2018). Safe dike heights at minimal costs: An integer programming approach. European Journal of Operational Research, 270(1), 294-301.