基于遗传算法与神经网络的水库水沙联合优化调度模型.pdfVIP

第33卷第2期 水 利 水 电科 技 进 展 2013年3月 Vol.33 No.2 Advances in Science and Technology of Water Resources Mar. 2013 DOI:10.3880/ j.issn.1006 7647.2013.02.003 基于遗传算法与神经网络的水库水沙联合优化调度模型 肖摇 杨,彭摇 杨,王太伟 (华北电力大学可再生能源学院,北京摇 102206) 摘要:针对一维泥沙数学模型维数高、求解耗时长以及水沙联合调度模型多目标难以求解的问题, 结合遗传算法与神经网络的特性,以发电量最大和有效库容最大为基本目标,构建了水库水沙联合 优化调度模型。 利用约束法和权重法,将多目标模型转化为单目标模型,采用加速遗传算法进行求 解,其中泥沙冲淤量使用自适应BP神经网络进行拟合预测。 三峡水库实例计算结果表明:运行 20a,与原设计运行方式相比,采用该优化调度模型优化运行年均发电量增加7郾732%,泥沙淤积量 增加0郾044%,在淤积量增加很小的情况下能大幅度增加发电量,模型能较好地解决水库水沙联合 调度问题,在工程实际中是有效可行的。 关键词:水沙联合优化调度;加速遗传算法;自适应BP神经网络;三峡水库 中图分类号:TV145摇 摇 摇 文献标志码:A摇 摇 摇 文章编号:1006 7647(2013)02 0009 05 Water鄄sediment coordinated optimized dispatch model of reservoir based on genetic algorithm and neural network/ / XIAOYang,PENGYang,WANGTaiwei(School of Renewable Energy,North ChinaElectric Power University, Beijing 102206,China) Abstract:In order to solve problems including multi鄄dimensions and long solution times of a one鄄dimensional sediment model,multi鄄objectives and the solution difficulty of a water鄄sediment coordinative dispatch model, a water鄄sediment coordinated optimized dispatch model was established on the basis of characteristics of genetic algorithms and neural networks. The model took the maximum power generation and effective storage as the elementary objects. The multi鄄 objective model can be transformed into a single鄄objective model with the method of restricting and weighting. The single鄄 objective model issolvedusingthemethodofacceleratinggeneticalgorithm. TheadaptiveBPneuralnetworkwasusedtofit the prediction for the sedimentation and scour. Three Gorges Reservoir case results show that the average annual electric energy production and the sedimentation and scour increase by 7郾732% and0