Assessing the weighted multi-objective adaptive surrogate model optimization to derive large-scale reservoir operating rules with sensitivity analysis

详细信息    查看全文

• 作者：Jingwen Zhang^a ; Xu Wang^b ; Pan Liu^a ; Xiaohui Lei^b ; ^lxh@iwhr.com ; Zejun Li^a ; Wei Gong^c ; Qingyun Duan^c ; Hao Wang^b
• 关键词：AGDP ; aggregation-decomposition method ; COR ; conventional operating rules ; SA ; Sensitivity analysis ; MARS ; multivariate adaptive regression splines ; LH ; Latin Hypercube ; MC ; Monte Carlo ; NSGAII ; non-dominated sorting genetic algorithm II ; WNSGAII ; weighted non-dominated sorting genetic algorithm II ; WMO-ASMO ; weighted multi-objective adaptive surrogate model optimization ; GLP ; Good Lattice Point ; RGS ; ranked Gram-Schmidt algorithm ; GPR ; Gaussian processes regression
• 刊名：Journal of Hydrology
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：544
• 期：Complete
• 页码：613-627
• 全文大小：3918 K
• 卷排序：544

文摘

Large-scale reservoir operating rules are derived by sensitive analysis and an adaptive surrogate model. Sensitivity analysis screens out the sensitive parameters of the large-scale reservoir operating rules. The weighted crowding distance of WNSGAII contributes to better performance than the classical NSGAII. WMO-ASMO outperforms NSGAII and WNSGAII with same original model runs.