大渡河中下游梯级水电站模拟优化运行研究  

Research on Optimal Operation of Cascade Hydropower Stations in Middle and Lower Reaches of Dadu River

作　　者：梁楚盛 邹祖建 黄炜斌[1] 马光文[1] LIANG Chusheng ZOU Zujian HUANG Weibin MA Guangwen(College of Water Resource and Hydropower, Sichuan University, Chengdu 610065, Sichuan, China Dadu River Hydropower Development Co., Ltd., Chengdu 610041, Sichuan, China)

机构地区：[1]四川大学水利水电学院,四川成都610065 [2]国电大渡河流域水电开发有限公司,四川成都610041

出　　处：《水力发电》2017年第3期98-101,共4页Water Power

基　　金：国家重点基础研究发展计划("973"计划)资助项目(2013CB036406-4);中国清洁发展机制基金赠款项目(2013114)

摘　　要：针对梯级水电站中长期来水不确定性的问题,依据长系列确定来水情况下的优化调度结果,建立门限回归、最近邻抽样回归和BP人工神经网络优化调度函数模型,模拟大渡河中下游梯级水电站的联合优化运行,将各模型的模拟优化调度结果与来水确定下的最优运行水位进行对比。结果表明,BP人工神经网络优化调度函数模型能够更好的模拟梯级水电站运行,对梯级水电站的实际优化运行具有参考意义。In view of the uncertainty of long-term inflow condition for cascade hydropower stations, the Threshold Regression model, Nearest Neighbor Bootstrapping Regressive （NNBR） model and BP Artificial Neural Network （BP-ANN） model are established respectively based on long series optimal operation results of stations to simulate the optimization operation of cascade hydropower stations in middle and lower reaches of Dadu River. The optimization operation simulation results of each model are compared with long-term optimal operation under certain inflow condition. The result proves that the BP Artificial Neural Network model is closer to optimal operation and can provide reference for the practical operation of cascade hydropower stations.

关 键 词：梯级水电站 优化运行 门限回归 最近邻抽样回归 BP人工神经网络 

分 类 号：TV737[水利工程—水利水电工程]