粒子群算法在水库防洪优化调度中的应用研究
|
摘要
我国长江流域洪涝灾害频繁,而中游地区是防洪重点。三峡水库对长江中游地区的防洪作用明显,但调度方式还是以调度图和调度规则为基础的常规调度,不能充分发挥其防洪作用。本文研究将粒子群优化算法应用到三峡水库对城陵矶站的防洪补偿调度优化模型中,以改进三峡水库的防洪效果。
粒子群优化算法是一种简单实用的群智能全局优化算法。自该算法提出以来,在各种工程领域都得到了广泛的应用。在水库优化调度调度领域也有一定的应用研究。但基本粒子群算法也有易早熟、收敛速度慢等缺陷。本文提出一种自适应粒子群改进算法,对基本粒子群算法进行了相关改进,提高其跳出局部最优的能力,并将其应用于设计洪水过程线推求、马斯京根洪水演进参数优化模型的求解中。
本文以1954年大洪水为资料,建立三峡对城陵矶防洪补偿调度优化模型,将水库调度约束条件和三峡水库特有的调度规则相融合,以城陵矶站分洪量最小为目标。利用自适应粒子群改进算法求解该优化模型。结果表明,城陵矶站的分洪量较小,优化效果较为明显,为水库防洪优化调度模型的求解提供了一种新方法。
本文又针对实际调度中需要关注的预报问题,提出利用人工神经网络建立城陵矶站流量短期预报模型,并对其进行相关试验和结果分析,指出该模型的缺陷,并加以改进。
Flood is frequent in Yangtze River basin, and the middle reach is the most important area. The Three Gorges Reservoir has an important effect in flood control of this area, but the operation mode still relies on regulation diagram and operation rules. This cannot maximize the effsct. This paper applies the Particle Swarm Optimization (PSO) to the Three Gorges Reservoir compensation operation to decreas flood divertion to the Chenglingji station.
PSO is a new, simple and praetieal optimization algorithm based on swarm intelligence. Since proposed, PSO has been widely used in various engineering fields including reservoir operation optimization. However, the classical PSO still has its inherent flaws, like fall into local optimum and low computing speed. This paper proposed an Improved Adaptive Particle Swarm Optimization (IA-PSO) to improve its ability of jumping out from local optimum.Then use it to solve the design flood flow curve, flood routing Muskingum parameter optimization model.
Using the flood in 1954 as an example, this paper establishs the Three Gorges Reservoir compensation operation on Chenglingji station model, which combined the constraint conditions of the Three Gorges Reservoir and its operation rules in target of minimum flood volume of Chenglingji station.The IA-PSO is used to solve the model. The results show that the flood volume diverted to Chenglingji station is decrease, and the effect of the optimization method is obvious.It provides a new way to solve the optimal operation models.
This paper also proposes a short-term inflow forecasting model of Chenglingji station by artificial neural network method, which is important on the flood real-time operation.Then pointed out the shortcomings of the model and make some improvements of this model based on the tests and results.
粒子群优化算法是一种简单实用的群智能全局优化算法。自该算法提出以来,在各种工程领域都得到了广泛的应用。在水库优化调度调度领域也有一定的应用研究。但基本粒子群算法也有易早熟、收敛速度慢等缺陷。本文提出一种自适应粒子群改进算法,对基本粒子群算法进行了相关改进,提高其跳出局部最优的能力,并将其应用于设计洪水过程线推求、马斯京根洪水演进参数优化模型的求解中。
本文以1954年大洪水为资料,建立三峡对城陵矶防洪补偿调度优化模型,将水库调度约束条件和三峡水库特有的调度规则相融合,以城陵矶站分洪量最小为目标。利用自适应粒子群改进算法求解该优化模型。结果表明,城陵矶站的分洪量较小,优化效果较为明显,为水库防洪优化调度模型的求解提供了一种新方法。
本文又针对实际调度中需要关注的预报问题,提出利用人工神经网络建立城陵矶站流量短期预报模型,并对其进行相关试验和结果分析,指出该模型的缺陷,并加以改进。
Flood is frequent in Yangtze River basin, and the middle reach is the most important area. The Three Gorges Reservoir has an important effect in flood control of this area, but the operation mode still relies on regulation diagram and operation rules. This cannot maximize the effsct. This paper applies the Particle Swarm Optimization (PSO) to the Three Gorges Reservoir compensation operation to decreas flood divertion to the Chenglingji station.
PSO is a new, simple and praetieal optimization algorithm based on swarm intelligence. Since proposed, PSO has been widely used in various engineering fields including reservoir operation optimization. However, the classical PSO still has its inherent flaws, like fall into local optimum and low computing speed. This paper proposed an Improved Adaptive Particle Swarm Optimization (IA-PSO) to improve its ability of jumping out from local optimum.Then use it to solve the design flood flow curve, flood routing Muskingum parameter optimization model.
Using the flood in 1954 as an example, this paper establishs the Three Gorges Reservoir compensation operation on Chenglingji station model, which combined the constraint conditions of the Three Gorges Reservoir and its operation rules in target of minimum flood volume of Chenglingji station.The IA-PSO is used to solve the model. The results show that the flood volume diverted to Chenglingji station is decrease, and the effect of the optimization method is obvious.It provides a new way to solve the optimal operation models.
This paper also proposes a short-term inflow forecasting model of Chenglingji station by artificial neural network method, which is important on the flood real-time operation.Then pointed out the shortcomings of the model and make some improvements of this model based on the tests and results.
引文
[1]黄锡荃,苏法崇,梅安新.中国的河流.北京:商务印书馆, 1995-3-1
[2]郑玉华.三峡新纪元.北京:中国档案出版社, 1998-7-1
[3] Litle J D C. The Use of Storage Water in a Hydroelectric System[J]. Operations Research, 1955(3): 187-197
[4] J S Windsor. Optimization Model for Reservoir Flood Control[J]. Water Resources Research, 1973, 9(5): 1103-1114
[5]神经网络原理. Simon Haykin著.叶世伟等译.北京:机械工业出版社, 2004-01
[6] Holland J H. Adaptation in Natural and artificial Systems[M]. Ann Arbor. The University of Michigan Predd, 1975
[7] S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi. Optimization by Simulated Annealing. Science, 1983, 220: 671-680
[8] DORIGO M. MANIEZZO V. COLORNIA. The ant system: optimization by a colonyof cooperating agents [J]. IEEE Transaction on Systems, 1996, 26 (1): 1 -26
[9] Kennedy J, Eberhart R. C. Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, IV. Piscataway, NJ: IEEE Servive Center, 1995. 1942~1948
[10]谢晓锋等.微粒群算法综述.控制与决策[J]. 2003, 18(2)
[11]刘波.粒子群优化算法及其工程应用.北京:电子工业出版社, 2010-8
[12]纪震等.粒子群算法及其应用.北京:科学出版社, 2009-01
[13] Kennedy J. The particle swarm: Social adaptation of knowledge[A. P roc IEEE Int Conf on Evolutionary Computation[C. Indiamapolis, 1997. 303~308
[14] ClercM. The swarm and the queen: Towards a deterministic and adaptive particle swarm optim ization[A. P roc of the Congress on Evolutionary Computation[C. W ashingtonDC, 1999. 1951~1957
[15] Levy A, MontalvoA. Topics in Global Optimization. New York: Springer-Verlag, 2006, 10(3): 281~295
[16] Angeline P J. U sing selection to improve particle swarm optim ization [A. P roc IEEE Int Conf onEvolutionary Computation [C]. Anchorage, 1998. 84~89
[17] Parsopoulos K E, Vrahatis M N. Recent approaches to global optimization problems through particle swarm optimization. Natrual Computing, 2002: 235~306
[18] Holland J H. A daptation in N atural and A rtificialSystem s [M]. Ann A rbor: U niversity of M ichiganPress, 1975
[19]刘波,潘宏侠.火炮身管热护套防护效率测试研究.兵工学报, 2010(8)
[20]刘海江,黄炜.基于粒子群算法的数控加工切削参数优化.同济大学学报(自然科学版), 2008, 36(6): 803~806
[21]程颖,鞠平,吴峰.负荷模型参数辨识的粒子群优化法及其与基因算法比较.电力系统自动化, 2003, 27(11): 25~29
[22]谢磊,王树青,张建明.基于PSO的间歇生产鲁棒统计过程监控.化工学报, 2005, 25(03): 492~498
[23]秦元庆,孙德宝,李宁.基于粒子群算法的移动机器人路径规划.机器人, 2004, 26(3): 222~225
[24]李爱国,张艳丽.基于PSO的软件结构测试数据自动生成方式.计算机工程, 2008, 34(06): 93~97
[25]原萍,王光兴,张洋洋.求解通信优化问题的一种微粒群优化方法.东北大学学报(自然科学版), 2004, 25(10): 934~937
[26]吴松.改进粒子群算法在并联水库群联合防洪优化调度中的应用.硕士论文, 2007. 06
[27]谢维,纪昌明,吴月秋,李新武.基于文化粒子群算法的水库防洪优化调度.水利学报, 2010, 41(4): 452~457
[28]邱林,肖琳.改进微粒群优化算法在水库防洪调度中的应用.人民黄河, 2007, 29(10): 18~21
[29]纪昌明,吴月秋,张验科.混沌粒子群优化算法在水库防洪优化调度中的应用.华北电力大学学报, 2008, 35(6): 103~107
[30]王国利,梁国华,彭勇,吕淑琦.基于PSO算法的水库防洪优化调度模型及应用.水电能源科学, 2009, 27(1): 74~76
[31]袁鹏,常江,朱兵,李彬.粒子群算法的惯性权重模型在水库防洪调度中的应用.四川大学学报, 2006, 38(5): 54~57
[32] Clerc M. Discrete Particle Swarm Optimization, Illustrated by the Traveling Saleman Problem. http: // www. mau-ricecierc. net, 2000
[33]庞巍,王康平,周春光,黄岚,季晓辉.模糊离散粒子群优化算法求解旅行商问题.小型微型计算机系统, 2005, 26(8): 1331~1334
[34] Brits, R., A. P. Engelbreeht, F. Vanden Bergh. A Niching Partiele Swarm Optimiler. In Proeeedings of the Conference on Simulated Evolution and Learning. November 2002
[35]王俊年,申群太,沈洪远,周鲜成.一种基于聚类的小生境微粒群算法.信息与控制, 134(34): 680~689
[36]高鹰,谢胜利.基于模拟退火的粒子群优化算法.计算机工程与应用, 2004(1): 47~50
[37]高鹰,谢胜利.混沌粒子群优化算法.计算机科学, 2004, 31(8): 13~15
[38] S. Dasctal.. Particle Swarm Optimization and Differential Evolution Algorithms: Technical Analysis, Applications and Hybridization Prespecitives, Studies in Computional Intelligence, 2008
[39]邱林等.滦河下游水库群联合调度研究.郑州:黄河水利出版社, 2009-05
[40]詹道江.叶守泽.工程水文学[M ].北京:中国水利水电出版社, 2000: 122-125
[41]翟国静.马斯京根模型参数估计方法探讨.北京:水文, 1997-3
[42]谢作涛,张小峰,谈广鸣.洞庭湖城陵矶流量逐日预报研究.武汉大学学报, 2004, 37(2): 5~7
[43]李成林,杨斌斌.基于BP神经网络和遗传算法的丰满水库洪水预报模型研究.东北水利水电, 2009, 08: 57~62
[44]李向阳,程春田,林剑艺.基于BP神经网络的贝叶斯概率水文预报模型.水利学报, 2006, 37(3): 354~359
[2]郑玉华.三峡新纪元.北京:中国档案出版社, 1998-7-1
[3] Litle J D C. The Use of Storage Water in a Hydroelectric System[J]. Operations Research, 1955(3): 187-197
[4] J S Windsor. Optimization Model for Reservoir Flood Control[J]. Water Resources Research, 1973, 9(5): 1103-1114
[5]神经网络原理. Simon Haykin著.叶世伟等译.北京:机械工业出版社, 2004-01
[6] Holland J H. Adaptation in Natural and artificial Systems[M]. Ann Arbor. The University of Michigan Predd, 1975
[7] S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi. Optimization by Simulated Annealing. Science, 1983, 220: 671-680
[8] DORIGO M. MANIEZZO V. COLORNIA. The ant system: optimization by a colonyof cooperating agents [J]. IEEE Transaction on Systems, 1996, 26 (1): 1 -26
[9] Kennedy J, Eberhart R. C. Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, IV. Piscataway, NJ: IEEE Servive Center, 1995. 1942~1948
[10]谢晓锋等.微粒群算法综述.控制与决策[J]. 2003, 18(2)
[11]刘波.粒子群优化算法及其工程应用.北京:电子工业出版社, 2010-8
[12]纪震等.粒子群算法及其应用.北京:科学出版社, 2009-01
[13] Kennedy J. The particle swarm: Social adaptation of knowledge[A. P roc IEEE Int Conf on Evolutionary Computation[C. Indiamapolis, 1997. 303~308
[14] ClercM. The swarm and the queen: Towards a deterministic and adaptive particle swarm optim ization[A. P roc of the Congress on Evolutionary Computation[C. W ashingtonDC, 1999. 1951~1957
[15] Levy A, MontalvoA. Topics in Global Optimization. New York: Springer-Verlag, 2006, 10(3): 281~295
[16] Angeline P J. U sing selection to improve particle swarm optim ization [A. P roc IEEE Int Conf onEvolutionary Computation [C]. Anchorage, 1998. 84~89
[17] Parsopoulos K E, Vrahatis M N. Recent approaches to global optimization problems through particle swarm optimization. Natrual Computing, 2002: 235~306
[18] Holland J H. A daptation in N atural and A rtificialSystem s [M]. Ann A rbor: U niversity of M ichiganPress, 1975
[19]刘波,潘宏侠.火炮身管热护套防护效率测试研究.兵工学报, 2010(8)
[20]刘海江,黄炜.基于粒子群算法的数控加工切削参数优化.同济大学学报(自然科学版), 2008, 36(6): 803~806
[21]程颖,鞠平,吴峰.负荷模型参数辨识的粒子群优化法及其与基因算法比较.电力系统自动化, 2003, 27(11): 25~29
[22]谢磊,王树青,张建明.基于PSO的间歇生产鲁棒统计过程监控.化工学报, 2005, 25(03): 492~498
[23]秦元庆,孙德宝,李宁.基于粒子群算法的移动机器人路径规划.机器人, 2004, 26(3): 222~225
[24]李爱国,张艳丽.基于PSO的软件结构测试数据自动生成方式.计算机工程, 2008, 34(06): 93~97
[25]原萍,王光兴,张洋洋.求解通信优化问题的一种微粒群优化方法.东北大学学报(自然科学版), 2004, 25(10): 934~937
[26]吴松.改进粒子群算法在并联水库群联合防洪优化调度中的应用.硕士论文, 2007. 06
[27]谢维,纪昌明,吴月秋,李新武.基于文化粒子群算法的水库防洪优化调度.水利学报, 2010, 41(4): 452~457
[28]邱林,肖琳.改进微粒群优化算法在水库防洪调度中的应用.人民黄河, 2007, 29(10): 18~21
[29]纪昌明,吴月秋,张验科.混沌粒子群优化算法在水库防洪优化调度中的应用.华北电力大学学报, 2008, 35(6): 103~107
[30]王国利,梁国华,彭勇,吕淑琦.基于PSO算法的水库防洪优化调度模型及应用.水电能源科学, 2009, 27(1): 74~76
[31]袁鹏,常江,朱兵,李彬.粒子群算法的惯性权重模型在水库防洪调度中的应用.四川大学学报, 2006, 38(5): 54~57
[32] Clerc M. Discrete Particle Swarm Optimization, Illustrated by the Traveling Saleman Problem. http: // www. mau-ricecierc. net, 2000
[33]庞巍,王康平,周春光,黄岚,季晓辉.模糊离散粒子群优化算法求解旅行商问题.小型微型计算机系统, 2005, 26(8): 1331~1334
[34] Brits, R., A. P. Engelbreeht, F. Vanden Bergh. A Niching Partiele Swarm Optimiler. In Proeeedings of the Conference on Simulated Evolution and Learning. November 2002
[35]王俊年,申群太,沈洪远,周鲜成.一种基于聚类的小生境微粒群算法.信息与控制, 134(34): 680~689
[36]高鹰,谢胜利.基于模拟退火的粒子群优化算法.计算机工程与应用, 2004(1): 47~50
[37]高鹰,谢胜利.混沌粒子群优化算法.计算机科学, 2004, 31(8): 13~15
[38] S. Dasctal.. Particle Swarm Optimization and Differential Evolution Algorithms: Technical Analysis, Applications and Hybridization Prespecitives, Studies in Computional Intelligence, 2008
[39]邱林等.滦河下游水库群联合调度研究.郑州:黄河水利出版社, 2009-05
[40]詹道江.叶守泽.工程水文学[M ].北京:中国水利水电出版社, 2000: 122-125
[41]翟国静.马斯京根模型参数估计方法探讨.北京:水文, 1997-3
[42]谢作涛,张小峰,谈广鸣.洞庭湖城陵矶流量逐日预报研究.武汉大学学报, 2004, 37(2): 5~7
[43]李成林,杨斌斌.基于BP神经网络和遗传算法的丰满水库洪水预报模型研究.东北水利水电, 2009, 08: 57~62
[44]李向阳,程春田,林剑艺.基于BP神经网络的贝叶斯概率水文预报模型.水利学报, 2006, 37(3): 354~359