• 全国中文核心期刊
  • 中国科技核心期刊
  • 美国工程索引(EI)收录期刊
XU Yueping, LU Haonan, YU Xinting, GUO Yuxue. Optimization of gate operation for reservoir flood control based on deep learning ensemble forecasting[J]. Advances in Water Science, 2024, 35(6): 900-913. DOI: 10.14042/j.cnki.32.1309.2024.06.004
Citation: XU Yueping, LU Haonan, YU Xinting, GUO Yuxue. Optimization of gate operation for reservoir flood control based on deep learning ensemble forecasting[J]. Advances in Water Science, 2024, 35(6): 900-913. DOI: 10.14042/j.cnki.32.1309.2024.06.004

Optimization of gate operation for reservoir flood control based on deep learning ensemble forecasting

Funds: The study is financially supported by the National Key R&D Program of China (No. 2021YFD1700802) and the Key R&D Program of Zhejiang Province, China (No. 2021C03017).
More Information
  • Received Date: June 18, 2024
  • Published Date: November 10, 2024
  • Research is needed for improving reservoir flood forecasting and operation to reduce flood-induced losses. Current reservoir flood control practices lack consideration of actual gate operations and dispatch scheme feasibility. This study proposes a refined flood operation optimization model, which takes into account inflow forecast uncertainties by utilizing ensemble forecasts derived from a combination of Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Transformer deep learning models. Gate discharge states and their durations are taken as decision variables. A case study was conducted in the Jiaojiang River basin, Zhejiang Province. Results indicate that the ensemble forecasts are improved by 4.6% in accuracy compared to single model forecasts, and the forecast uncertainty is reliable for reservoir operation. The refined flood operation optimization model shows significant advantages over conventional methods, reducing the average maximum water level at the dam by 0.43 m and the average flood peak flow at downstream control section by 32.9 m3/s. The effectiveness of the optimized solution is less affected by inflow uncertainties. Overall, the proposed refined model is demonstrated to have the potential to provide valuable information to support reservoir flood control decision-making.

  • [1]
    徐宗学,陈浩,任梅芳,等. 中国城市洪涝致灾机理与风险评估研究进展[J]. 水科学进展,2020,31(5):713-724. (XU Z X,CHEN H,REN M F,et al. Progress on disaster mechanism and risk assessment of urban flood/waterlogging disasters in China[J]. Advances in Water Science,2020,31(5):713-724. (in Chinese)

    XU Z X, CHEN H, REN M F, et al. Progress on disaster mechanism and risk assessment of urban flood/waterlogging disasters in China[J]. Advances in Water Science, 2020, 31(5): 713-724. (in Chinese)
    [2]
    周研来,郭生练,王俊,等. 金沙江下游梯级水库汛期运行水位协同浮动调度研究[J]. 水利学报,2023,54(6):633-643. (ZHOU Y L,GUO S L,WANG J,et al. Study on synergetic control of flood operating water levels of cascade reservoirs in the downstream reach of the Jinsha River basin[J]. Journal of Hydraulic Engineering,2023,54(6):633-643. (in Chinese)

    ZHOU Y L, GUO S L, WANG J, et al. Study on synergetic control of flood operating water levels of cascade reservoirs in the downstream reach of the Jinsha River basin[J]. Journal of Hydraulic Engineering, 2023, 54(6): 633-643. (in Chinese)
    [3]
    YU X T,XU Y P,GU H T,et al. Multi-objective robust optimization of reservoir operation for real-time flood control under forecasting uncertainty[J]. Journal of Hydrology,2023,620:129421. doi: 10.1016/j.jhydrol.2023.129421
    [4]
    DEVI D,KUMAR SARMA A. Optimal advanced release scheme based on effective forecast horizon to minimize flood at downstream of a hydroelectric project[J]. Journal of Hydrology,2024,631:130822.
    [5]
    赵泽谦,黄强,明波,等. 基于多模型随机组合的水文集合预报方法研究[J]. 水力发电学报,2021,40(1):76-87. (ZHAO Z Q,HUANG Q,MING B,et al. Hydrological ensemble forecasting method based on stochastic combination of multiple models[J]. Journal of Hydroelectric Engineering,2021,40(1):76-87. (in Chinese) doi: 10.11660/slfdxb.20210108

    ZHAO Z Q, HUANG Q, MING B, et al. Hydrological ensemble forecasting method based on stochastic combination of multiple models[J]. Journal of Hydroelectric Engineering, 2021, 40(1): 76-87. (in Chinese) doi: 10.11660/slfdxb.20210108
    [6]
    MADDU R,PRADHAN I,AHMADISHARAF E,et al. Short-range reservoir inflow forecasting using hydrological and large-scale atmospheric circulation information[J]. Journal of Hydrology,2022,612:128153. doi: 10.1016/j.jhydrol.2022.128153
    [7]
    CASTANGIA M,GRAJALES L M M,ALIBERTI A,et al. Transformer neural networks for interpretable flood forecasting[J]. Environmental Modelling & Software,2023,160:105581.
    [8]
    李建柱,李磊菁,冯平,等. 基于深度学习的雷达降雨临近预报及洪水预报[J]. 水科学进展,2023,34(5):673-684. (LI J Z,LI L J,FENG P,et al. Radar rainfall nowcasting and flood forecasting based on deep learning[J]. Advances in Water Science,2023,34(5):673-684. (in Chinese)

    LI J Z, LI L J, FENG P, et al. Radar rainfall nowcasting and flood forecasting based on deep learning[J]. Advances in Water Science, 2023, 34(5): 673-684. (in Chinese)
    [9]
    刘成帅,孙悦,胡彩虹,等. 考虑产流模式空间分布的流域-城市复合系统洪水预报模型[J]. 水科学进展,2023,34(4):530-540. (LIU C S,SUN Y,HU C H,et al. Study on flood forecasting model of watershed-urban complex system considering the spatial distribution of runoff generation pattern[J]. Advances in Water Science,2023,34(4):530-540. (in Chinese)

    LIU C S, SUN Y, HU C H, et al. Study on flood forecasting model of watershed-urban complex system considering the spatial distribution of runoff generation pattern[J]. Advances in Water Science, 2023, 34(4): 530-540. (in Chinese)
    [10]
    刘成帅,解添宁,李文忠,等. 考虑径流过程矢量化的机器学习洪水预报模型[J]. 水科学进展,2024,35(3):420-429. (LIU C S,XIE T N,LI W Z,et al. Machine learning-based flood forecasting models considering runoff process vectorization[J]. Advances in Water Science,2024,35(3):420-429. (in Chinese)

    LIU C S, XIE T N, LI W Z, et al. Machine learning-based flood forecasting models considering runoff process vectorization[J]. Advances in Water Science, 2024, 35(3): 420-429. (in Chinese)
    [11]
    邹强,王学敏,李安强,等. 基于并行混沌量子粒子群算法的梯级水库群防洪优化调度研究[J]. 水利学报,2016,47(8):967-976. (ZOU Q,WANG X M,LI A Q,et al. Optimal operation of flood control for cascade reservoirs based on parallel chaotic quantum particle swarm optimization[J]. Journal of Hydraulic Engineering,2016,47(8):967-976. (in Chinese)

    ZOU Q, WANG X M, LI A Q, et al. Optimal operation of flood control for cascade reservoirs based on parallel chaotic quantum particle swarm optimization[J]. Journal of Hydraulic Engineering, 2016, 47(8): 967-976. (in Chinese)
    [12]
    唐金杰. 基于离散粒子群算法的水库防洪调度优化研究[J]. 水利技术监督,2022,30(9):190-194. (TANG J J. Optimization of reservoir flood control operation based on discrete particle swarm optimization[J]. Technical Supervision in Water Resources,2022,30(9):190-194. (in Chinese) doi: 10.3969/j.issn.1008-1305.2022.09.049

    TANG J J. Optimization of reservoir flood control operation based on discrete particle swarm optimization[J]. Technical Supervision in Water Resources, 2022, 30(9): 190-194. (in Chinese) doi: 10.3969/j.issn.1008-1305.2022.09.049
    [13]
    黄显峰,吴志远,李昌平,等. 基于改进粒子群-逐次逼近法的水库调度图多目标优化[J]. 水利水电科技进展,2021,41(2):1-7. (HUANG X F,WU Z Y,LI C P,et al. Multi-objective optimization of reservoir operation chart based on IPSO-DPSA[J]. Advances in Science and Technology of Water Resources,2021,41(2):1-7. (in Chinese)

    HUANG X F, WU Z Y, LI C P, et al. Multi-objective optimization of reservoir operation chart based on IPSO-DPSA[J]. Advances in Science and Technology of Water Resources, 2021, 41(2): 1-7. (in Chinese)
    [14]
    陈立华,梅亚东,董雅洁,等. 改进遗传算法及其在水库群优化调度中的应用[J]. 水利学报,2008,39(5):550-556. (CHEN L H,MEI Y D,DONG Y J,et al. Improved genetic algorithm and its application in optimal dispatch of cascade reservoirs[J]. Journal of Hydraulic Engineering,2008,39(5):550-556. (in Chinese) doi: 10.3321/j.issn:0559-9350.2008.05.006

    CHEN L H, MEI Y D, DONG Y J, et al. Improved genetic algorithm and its application in optimal dispatch of cascade reservoirs[J]. Journal of Hydraulic Engineering, 2008, 39(5): 550-556. (in Chinese) doi: 10.3321/j.issn:0559-9350.2008.05.006
    [15]
    肖刚,解建仓,罗军刚. 基于改进NSGA II的水库多目标防洪调度算法研究[J]. 水力发电学报,2012,31(5):77-83. (XIAO G,XIE J C,LUO J G. Improved NSGAⅡ algorithm for flood dispatching of multi-objectives reservoir[J]. Journal of Hydroelectric Engineering,2012,31(5):77-83. (in Chinese)

    XIAO G, XIE J C, LUO J G. Improved NSGAⅡ algorithm for flood dispatching of multi-objectives reservoir[J]. Journal of Hydroelectric Engineering, 2012, 31(5): 77-83. (in Chinese)
    [16]
    黄显峰,王宁,刘志佳,等. 基于改进NSGA-Ⅱ算法的梯级水库多目标优化调度[J]. 水利水电科技进展,2024,44(4):51-58. (HUANG X F,WANG N,LIU Z J,et al. Multi-objective optimal operation of cascade reservoirs based on improved NSGA-Ⅱ algorithm[J]. Advances in Science and Technology of Water Resources,2024,44(4):51-58. (in Chinese)

    HUANG X F, WANG N, LIU Z J, et al. Multi-objective optimal operation of cascade reservoirs based on improved NSGA-Ⅱ algorithm[J]. Advances in Science and Technology of Water Resources, 2024, 44(4): 51-58. (in Chinese)
    [17]
    CHEN J,ZHONG P G,LIU W F,et al. A multi-objective risk management model for real-time flood control optimal operation of a parallel reservoir system[J]. Journal of Hydrology,2020,590:125264.
    [18]
    HUANG X,XU B,ZHONG P G,et al. Robust multiobjective reservoir operation and risk decision-making model for real-time flood control coping with forecast uncertainty[J]. Journal of Hydrology,2022,605:127334. doi: 10.1016/j.jhydrol.2021.127334
    [19]
    GUO Y X,XU Y P,YU X T,et al. AI-based ensemble flood forecasts and its implementation in multi-objective robust optimization operation for reservoir flood control[J]. Water Resources Research,2024,60(5):e2023WR035693. doi: 10.1029/2023WR035693
    [20]
    ZHANG J W,LI Z J,WANG X,et al. A novel method for deriving reservoir operating rules based on flood classification-aggregation-decomposition[J]. Journal of Hydrology,2019,568:722-734. doi: 10.1016/j.jhydrol.2018.10.032
    [21]
    PAN Z H,CHEN L H,TENG X. Research on joint flood control operation rule of parallel reservoir group based on aggregation–decomposition method[J]. Journal of Hydrology,2020,590:125479.
    [22]
    ZHU D,CHEN H,ZHOU Y L,et al. Exploring a multi-objective cluster-decomposition framework for optimizing flood control operation rules of cascade reservoirs in a river basin[J]. Journal of Hydrology,2022,614:128602. doi: 10.1016/j.jhydrol.2022.128602
    [23]
    朱迪,周研来,陈华,等. 考虑分级防洪目标的梯级水库汛控水位调度模型及应用[J]. 水利学报,2023,54(4):414-425. (ZHU D,ZHOU Y L,CHEN H,et al. An operation model of flood control water levels of cascade reservoirs considering grading flood control objectives and its application[J]. Journal of Hydraulic Engineering,2023,54(4):414-425. (in Chinese)

    ZHU D, ZHOU Y L, CHEN H, et al. An operation model of flood control water levels of cascade reservoirs considering grading flood control objectives and its application[J]. Journal of Hydraulic Engineering, 2023, 54(4): 414-425. (in Chinese)
    [24]
    陈森林,张亚文,李丹. 水库防洪优化调度的恒定出流模型及应用[J]. 水科学进展,2021,32(5):683-693. (CHEN S L,ZHANG Y W,LI D. Study on constant outflow model for reservoir flood control operation and its application[J]. Advances in Water Science,2021,32(5):683-693. (in Chinese)

    CHEN S L, ZHANG Y W, LI D. Study on constant outflow model for reservoir flood control operation and its application[J]. Advances in Water Science, 2021, 32(5): 683-693. (in Chinese)
    [25]
    王靖,鄢尚,陈仕军,等. 考虑闸门实际运行的雅砻江下游梯级水库联合防洪优化调度[J]. 四川大学学报(工程科学版),2014,46(4):20-25. (WANG J,YAN S,CHEN S J,et al. Flood control optimal operation on cascade reservoirs of downstream yalong river considering actual running of floodgate[J]. Journal of Sichuan University (Engineering Science Edition),2014,46(4):20-25. (in Chinese)

    WANG J, YAN S, CHEN S J, et al. Flood control optimal operation on cascade reservoirs of downstream yalong river considering actual running of floodgate[J]. Journal of Sichuan University (Engineering Science Edition), 2014, 46(4): 20-25. (in Chinese)
    [26]
    KIM Y G,SUN B Q,KIM P,et al. A study on optimal operation of gate-controlled reservoir system for flood control based on PSO algorithm combined with rearrangement method of partial solution groups[J]. Journal of Hydrology,2021,593:125783. doi: 10.1016/j.jhydrol.2020.125783
    [27]
    HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780. doi: 10.1162/neco.1997.9.8.1735
    [28]
    郭玉雪,许月萍,陈浩,等. 基于多种递归神经网络的海岛水库径流预报[J]. 水力发电学报,2021,40(9):14-26. (GUO Y X,XU Y P,CHEN H,et al. Reservoir inflow forecasting for island areas based on multiple recurrent neural networks[J]. Journal of Hydroelectric Engineering,2021,40(9):14-26. (in Chinese) doi: 10.11660/slfdxb.20210902

    GUO Y X, XU Y P, CHEN H, et al. Reservoir inflow forecasting for island areas based on multiple recurrent neural networks[J]. Journal of Hydroelectric Engineering, 2021, 40(9): 14-26. (in Chinese) doi: 10.11660/slfdxb.20210902
    [29]
    VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[J]. Neural Information Processing Systems, 2017, 5998:6008.
    [30]
    董磊华,熊立华,万民. 基于贝叶斯模型加权平均方法的水文模型不确定性分析[J]. 水利学报,2011,42(9):1065-1074. (DONG L H,XIONG L H,WAN M. Uncertainty analysis of hydrological modeling using the Bayesian Model Averaging Method[J]. Journal of Hydraulic Engineering,2011,42(9):1065-1074. (in Chinese)

    DONG L H, XIONG L H, WAN M. Uncertainty analysis of hydrological modeling using the Bayesian Model Averaging Method[J]. Journal of Hydraulic Engineering, 2011, 42(9): 1065-1074. (in Chinese)
    [31]
    DEB K. An efficient constraint handling method for genetic algorithms[J]. Computer methods in applied mechanics and engineering,2000,186(2/3/4):311-338.
  • Cited by

    Periodical cited type(20)

    1. 张攀全,管镇,李红刚,杨庆. 变化环境下澜沧江梯级电站运行对湄公河枯水期的影响. 长江科学院院报. 2025(01): 35-43 .
    2. 李帅,曾凌,熊斌,曹瑞,龚文婷,朱文丽. 长江上游近61年来水文干旱演变特征及归因. 水力发电学报. 2024(02): 33-45 .
    3. 王乐扬,张建云,宁忠瑞,贾雨凡,孙高霞,王国庆. 环境变化对澜沧江出境水文过程变异的影响. 水科学进展. 2024(02): 313-324 . 本站查看
    4. 耿雪兰. 水利工程在应对极端气候事件中的策略与实践. 水上安全. 2024(06): 181-183 .
    5. 王乐扬,张建云,宁忠瑞,贾雨凡,郭心仪,张睿,鲍振鑫. 气候变化对南方典型小水电站入库径流及发电的影响. 水利水运工程学报. 2024(02): 1-9 .
    6. 向燕芸,王弋,陈亚宁,张齐飞,张玉杰. 基于CMIP6模式的叶尔羌河流域未来水文干旱风险预估. 干旱区地理. 2024(05): 798-809 .
    7. 陈仕豪,门宝辉,庞金凤,张腾,王红瑞. 黄河流域非平稳气象干旱特征的重构及时空演变规律. 水力发电学报. 2024(07): 1-13 .
    8. 王云,李文鑫,张建云,刘翠善,阮俞理,虞畅,金君良,王国庆,贺瑞敏. 长江上游流域水文干旱历史演变及未来预估. 中国工程科学. 2024(06): 157-168 .
    9. 智协飞,田云涛,陈昌春,张余庆. 干旱传播研究进展与展望Ⅰ——干旱传播含义、特征、类型与研究方法. 南水北调与水利科技(中英文). 2023(04): 625-653 .
    10. 邓鹏,徐进超,王欢. 基于CMIP6的气候变化对鄱阳湖流域径流影响研究. 水利水运工程学报. 2023(04): 71-80 .
    11. 谭豪,脱云飞,王倩,郑阳,王飞,王昭仪,刘香凝,石小兰,丁明净,马继敏. 基于CRITIC-VIKOR法的云南省水资源承载力综合评价. 水资源与水工程学报. 2023(04): 118-126 .
    12. 马明卫,王召航,臧红飞,王文川,卫孟茹,崔惠娟. 基于SSP情景的黄河源区未来径流模拟预估. 华北水利水电大学学报(自然科学版). 2023(05): 31-40 .
    13. 张丹,梁瀚续,何小聪,时玉龙. 基于CMIP6的金沙江流域径流及水文干旱预估. 水资源保护. 2023(06): 53-62 .
    14. 霍艾迪,赵志欣,王星,杨璐莹,钟芳倩,陈建. 马莲河流域固沟保塬工程水文响应变化及优化. 水科学进展. 2023(06): 867-876 . 本站查看
    15. 葛路,詹良通,江衍铭. 气候变化对元江流域水文过程的影响. 中国农村水利水电. 2022(04): 41-49+56 .
    16. 石朋,詹慧婕,瞿思敏,冯进,管晓祥. 黄河源区气象干旱与水文干旱关联性分析. 水资源保护. 2022(03): 80-86 .
    17. 许拯民,林睿,左向菊,李想. 基于SWAT模型的沁河流域短中长期综合干旱指数构建及适用性分析. 中国农村水利水电. 2022(06): 76-83+89 .
    18. 张振东,罗斌,覃晖,唐海华,周超,冯快乐. 风光水互补系统时间序列变量概率预报框架. 水利学报. 2022(08): 949-963 .
    19. 熊景华,郭靖,郭生练,李娜,王俊,尹家波,唐俊龙. 基于多源降水数据估算澜湄流域可能最大降水. 水力发电学报. 2022(09): 77-86 .
    20. 龙笛,韩忠颖,王一鸣. 变化环境下澜沧江-湄公河流域干旱趋势. 水科学进展. 2022(05): 766-779 . 本站查看

    Other cited types(10)

Catalog

    Article Metrics

    Article views (196) PDF downloads (126) Cited by(30)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return