臺灣地區因降雨時空分布不均、地理環境不佳，加上地狹人稠，隨著都市、工商業發展，需水量大增，故水庫成為調節時空降雨不均與分配水資源之最重要設施之一。
本研究主要目的為探討水庫之退水段(洪峰發生後階段)最佳操作策略，以石門水庫為研究對象，透過遺傳演算法(Genetic Algorithm)搜尋最佳操作策略，設定蓄水功能與閘門操作次數最少為目標函數，並且根據石門水庫運轉規則以及河川自然流態，訂定限制式；本研究之目標函數最少兩種，但兩種目標不互相衝突，可合併為單目標進行搜尋。本研究將颱風場次依照平均入流量分類為大、中、小場次，透過GA搜尋結果與原始操作結果進行比較，結果顯示GA獲得較佳之操作結果，並且整體上皆能搜尋出符合限制條件之合理放流歷程。綜合結果得知GA操作不論於大、中、小場次、低水位或高水位皆能提供有效之退水段最佳操作策略。

In Taiwan, due to the uneven temporal distribution of rainfall and the poor geographical conditions, rivers cannot provide stable water resources for usage. With a large population living and industrial development in this small region, reservoirs become one of the important and effective floodwater storage facilities to adjust and distribute water resources.
For providing information of rational operating decisions in flood recession limb of reservoirs, this study proposed a reservoir operation optimization model, the desired storage and the minimum number of gate operation, with existing operational regulations and natural flow regime, taking Shihmen Reservoir as a case study. These two objective functions can combine into one objective function without conflict with each other by using the Genetic Algorithm (GA) as a searching engine to find the optimal operation strategy. In this study, according the average inflow, typhoons are classified into large, medium, and small events. In any cases, the results demonstrate that GA can effectively provide rational flood recession limb operating decision of the reservoir to store floodwater for the future usage and the few number of gate operation.

謝誌	I
中文摘要	III
Abstract	IV
目錄	VI
圖目錄	VIII
表目錄	X
第一章　前言	1
1.1　研究緣起與目的	1
1.2　研究流程	2
1.3　論文架構	4
第二章　文獻回顧	5
2.1　遺傳演算法之發展研究	5
2.2　遺傳演算法應用於水庫方面之研究	7
第三章　理論概述	10
3.1　遺傳演算法	10
3.2　遺傳演算法之基本架構與流程	11
3.3　遺傳演算法之基本元素與運算子	13
3.4　遺傳演算法之目標函數與限制式	25
第四章　研究案例	26
4.1　研究區域概述	26
4.2　颱風資料蒐集	29
4.3　目標函數與限制式	32
4.5　修正遺傳演算法	39
4.6　遺傳演算法之參數設定	41
第五章　結果與討論	42
5.1　大場次颱風操作比較	46
5.2　中場次颱風操作比較	50
5.3　小場次颱風操作比較	54
第六章　結論與建議	58
6.1　結論	58
6.2　建議	60
參考文獻	61
附錄　GA搜尋結果圖	67

圖1-1研究流程圖	3
圖3-1遺傳演算法流程圖	12
圖3-2遺傳演算法遺傳單元之資料結構	12
圖3-3二位元編碼	13
圖3-4實數編碼	13
圖3-5輪盤式選取法示意圖	16
圖3-6單點交配示意圖	18
圖3-7雙點交配示意圖	18
圖3-8字罩交配示意圖	19
圖3-9均勻交配示意圖	20
圖3-10突變示意圖	23
圖3-11反轉示意圖	23
圖4-1石門水庫位置圖	27
圖4-2退水段起訖時間選取示意圖	30
圖4-3修正前遺傳演算法結果示意圖	40
圖4-4放流量範圍修正示意圖	40
圖5-1 1979年歐敏颱風之GA操作放流歷程圖	47
圖5-2 1979年歐敏颱風之原始操作放流歷程圖	47
圖5-3 1992年寶莉颱風之GA操作放流歷程圖	49
圖5-4 1992年寶莉颱風之原始操作放流歷程圖	49
圖5-5 2004年蘭寧颱風之GA操作放流歷程圖	51
圖5-6 2004年蘭寧颱風之原始操作放流歷程圖	51
圖5-7 2006年珊珊颱風之GA操作放流歷程圖	53
圖5-8 2006年珊珊颱風之原始操作放流歷程圖	53
圖5-9 2008年卡玫基颱風之GA操作放流歷程圖	55
圖5-10 2008年卡玫基颱風之原始操作放流歷程圖	55
圖5-11 2016年莫蘭蒂颱風之GA操作放流歷程圖	57
圖5-12 2016年莫蘭蒂颱風之原始操作放流歷程圖	57

表4-1石門水庫主要設施及相關水門	28
表4-2颱風資料	31
表4-3水庫軟硬體條件總限制式整理表	35
表4-4 72場颱風場次之各範圍入流減少量平均值	39
表4-5遺傳演算法之參數設定	41
表5-1颱風場次分類	43
表5-2 GA與原始操作之比較結果	44

1.	Afshar A, Haddad O.B, Marino M.A, Adams B.J. (2007) Honey-bee mating optimization (HBMO) algorithm for optimal reservoir operation. J Frankl Inst 344:452–462.
2.	Ahmed J.A., Sarma A.K. (2005). Genetic Algorithm for Optimal Operating Policy of a Multipurpose Reservoir. Water Resources Management 19 (2): 145–61.
3.	Bhesdadiya R.H, Trived I.N, Jangir P, Jangir N, Kumar A. (2016) An NSGA-III Algorithm for Solving Multi-Objective Economic/Environmental Dispatch Problem. Edited by Victor Sreeram.
4.	Chang L.C. (2008). Guiding Rational Reservoir Flood Operation Using Penalty-Type Genetic Algorithm. Journal of Hydrology 354 (1): 65–74.
5.	Chang F.J, Chang L.C. (1998) Real-Coded Genetic Algorithm for Rule-Based Flood Control Reservoir Management.” Water Resources Management 12 (3): 185–98.
6.	Chang L.C, Chang F.J. (2001). Intelligent control for modelling of real-time reservoir operation. Hydrol Process 15:1621–1634.
7.	Chang F.J, Chen L, Chang L.C. (2005) Optimizing the reservoir operating rule curves by genetic algorithms.Hydrol Process 19:2277-2289.
8.	Chang F.J, Chang Y.T. (2006) Adaptive Neuro-Fuzzy Inference System for Prediction of Water Level in Reservoir. Advances in Water Resources 29 (1): 1–10.
9.	Chang L, Chang F.J. (2007) Applying a real-coded multi-population genetic algorithm to multi-reservoir operation.
10.	Chang L.C, Chang F.J, Wang K.W, Dai S.Y. (2010) Constrained Genetic Algorithms for Optimizing Multi-Use Reservoir Operation. Journal of Hydrology 390 (1): 66–74.
11.	Chang L.C, Ho C.C, Chen Y.W. (2010) Applying multiobjective genetic algorithm to analyze the conflict among different water use sectors during drought period. Journal of Water Resources Planning and Management, 136(5), 539-546.
12.	Cai X, McKinney D.C, Lasdon L.S. (2001). Solving Nonlinear Water Management Models Using a Combined Genetic Algorithm and Linear Programming Approach. Advances in Water Resources 24 (6): 667–76.
13.	Celeste A.B, Suzuki K, Kadota A. (2004). Genetic Algorithms for Real-Time Operation of Multipurpose Water Resource Systems. Journal of Hydroinformatics 6 (1): 19–38.
14.	Davis L. (1989). Adapting Operator Probabilities in Genetic Algorithms. Proc. of the Third Int. Conf. on Genetic Algorithms, J. David Schaffer (Ed.) (Morgan Kaufmann Publishers,San Mateo), 61–69.
15.	Davis L. (1991). Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York.
16.	Deb K. (1999) An Introduction to Genetic Algorithms. Sadhana, 24, 293-315.
17.	Deb K. (2000) An efficient constraint handling method for genetic algorithms. Comput Method Appl M.186:311–338.
18.	Deb K, Agrawal R.B. (1995b). Simulated Binary Crossover for Continuous Search Space.Complex Systems 9, 115–148.
19.	Deb K, Kumar A. (1995a). Real Coded Genetic Algorithms with Simulated Binary Crossover: Studies on Multimodal and Multiobjective Problems. Complex Systems 9,431–454.
20.	Deb K, Pratap A, Agarwal S. Meyarivan T.A.M.T. (2002) A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6, 182-197.
21.	Elfeky E.Z, Sarker R.A, Essam D.L. (2006).A Simple Ranking and Selection for Constrained Evolutionary Optimization. In Simulated Evolution and Learning, 537–44.Lecture Notes in Computer Science. Springer, Berlin, Heidelberg.
22.	Eshelman L.J, Schaffer J.D. (1993) Real-Coded Genetic Algorithms and Interval-Schemata. In Foundations of Genetic Algorithms, edited by L. DARRELL Whitley, 2:187–202. Foundations of Genetic Algorithms. Elsevier.
23.	Fonseca C.M, Fleming P.J. (1993) Genetic algorithms for multiobjective optimization:Formulation,discussion,and generalization. in Forrest, S., Ed., Proceedings of the Fifth International Conference on Genetic Algorithms, Morgan Kaufmann, San Mateo, California, pp.416–423.
24.	Fonseca C.M, Fleming P.J. (1995) An Overview of Evolutionary Algorithms in Multiobjective Optimization. Evolutionary Computation, Vol. 3, No. 1, 1995, pp. 1-16.
25.	Fonseca C.M, Fleming P.J. (1998a) Multiobjective optimization and multiple constraint handling with evolutionary algorithms-part I: a unified formulation. IEEE Trans Syst Man Cybern A 28:26-37
26.	Fonseca C.M, Fleming P.J. (1998b) Multiobjective optimization and multiple constraint handling with evolutionary algorithms-part II: application example. IEEE Trans Syst Man Cybern A 28:38-47
27.	Goldberg D.E. (1985) Optimal initial population size for binary-coded genetic algorithms. TCGA Report No. 85001, University of Alabama, Tuscaloosa.
28.	Goldberg D.E. (1989) Genetic Algorithms in Search, Optimization, and Machine Learning.Addison-Wesley Longman Publishing Co. Inc., Boston, MA, USA.
29.	Goldberg D.E, Deb K. (1991) A Comparative Analysis of Selection Schemes Used in Genetic Algorithms. In: Rawlins, G., Ed., Foundations of Genetic Algorithms, Morgan Kaufmann Publishers, San Mateo, CA, 69-93.
30.	García Nieto P.J, Alonso Fernández J.R, de Cos Juez F.J, Sánchez Lasheras F, Díaz Muñiz C. (2013). Hybrid Modelling Based on Support Vector Regression with Genetic Algorithms in Forecasting the Cyanotoxins Presence in the Trasona Reservoir (Northern Spain). Environmental Research 122 (April): 1–10.
31.	Haupt R.L, Haupt S.E. (1998) Practical Genetic Algorithms. New York, NY, USA: John Wiley & Sons, Inc.
32.	Holland J.H. (1975) Adaptation in Natural and Artificial Systems,University of Michigan Press, Ann Arbor.
33.	Heinz M, Dirk S.V. (1993). Predictive Models for the Breeder Genetic Algorithm I. Continuous Parameter Optimization. Evolutionary Computation 1, 25–49.
34.	Kim T, Heo J.H, Bae D.H, Kim J.H. (2008). Single-Reservoir Operating Rules for a Year Using Multiobjective Genetic Algorithm. Journal of Hydroinformatics 10 (2): 163–79.
35.	Lucasius C.B, Kateman G. (1989). Applications of genetic algorithms in chemometrics. Proc. of the Third International Conference on Genetic Algorithms, J. David Schaffer (Ed.) (Morgan Kaufmann Publishers, San Mateo), 170–176.
36.	Michalewicz Z. (1991). A Genetic Algorithms for the Linear Transportation Problem. IEEE Trans. on Systems, Man, and Cybernetics 21(2), 445–452.
37.	Michalewicz Z. (1992). Genetic Algorithms + Data Structures = Evolution Programs. SpringerVerlag, New York.
38.	Michalewicz Z. (1996) Genetic Algorithms + Data Structures=Evolution Programs (3rd Ed.). London, UK, UK: Springer-Verlag.
39.	Niazi A, Leardi R. (2012) Genetic Algorithms in Chemometrics. Journal of Chemometrics 26 (6): 345–51.
40.	Srinivas N.Deb K. (1995) Multiobjective optimization using nondominated sorting in genetic algorithms.Evolutionary Computation, Vol. 2, No. 3, pp. 221–248.
41.	Srinivas M, Patnaik L.M. (1994) Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms. IEEE Transactions on Systems, Man, and Cybernetics 24 (4): 656–67.
42.	Wright A.H. (1991).Genetic Algorithms for Real Parameter Optimization. In Foundations of Genetic Algorithms, edited by GREGORY J. E. Rawlins, 1:205–18.
43.	Wright A. (1991) Genetic algorithms for real parameter optimization, in: G. J. E. Rawlins, (ed.),Foundations of Genetic Algorithms, Morgan Kaufmann, San Mateo, CA, pp. 205–218.
44.	Wang Q. J. (1991) The genetic algorithm and its application to calibrating conceptual rainfall-runoff models. Water Resour. Res. 27(9), 2467.
45.	Wardlaw R, Sharif M. (1999). Evaluation of Genetic Algorithms for Optimal Reservoir System Operation. Journal of Water Resources Planning and Management 125 (1): 25–33.
46.	陳正炎、姚嘉耀、謝馥揚、廖苑雅，2006，運用遺傳演算法推求水庫操作規線之研究－以明德水庫為例，中華水土保持學報，37卷2期，P173-184
47.	王國威，2006，運用懲罰機制遺傳演算法於水庫洪颱操作之規劃，淡江大學水資源及環境工程學系研究所碩士論文
48.	蕭政宗、黃景裕，以遺傳演算法推導考量二衝突缺水指標之南化水庫多標的最佳限水策略，農業工程學報，56卷4期，P27-41
49.	楊舜年，2015，建立颱洪時期抽水站智慧型最佳化操作規則，台灣大學生物環境系統工程學研究所碩士論文
50.	洪彥甯、蕭政宗，2017，南化水庫最佳化與模糊化營運規線對缺水影響探討，農業工程學報，63卷2期，P67-77
51.	陳鵬安，2017，機器學習法於水庫異重流到達時間及排砂效率預報之研究，臺灣大學土木工程學研究所學位論文
52.	温庭玄，2017，運用多目標水庫最佳化操作提升水、糧食、能源之協同效益，臺灣大學生物環境系統工程學研究所學位論文
53.	李翊愷，2017，以NSGA-II探討平行水庫防洪操作策略，淡江大學水資源及環境工程學系研究所碩士論文