李世林,王李东,刘晓阳,马光文,黄炜斌,朱燕梅

• 1:四川大学水利水电学院
• 2:中国长江电力股份有限公司

摘要(Abstract)：

【目的】准确的径流式水电站出力预测对于拟定发电调度计划、电力保供策略至关重要。针对径流式水电站发电出力随机性强，直接预测精度低等特点，提出一种基于自适应变分模态分解和时间卷积网络(TCN)的组合预测模型。【方法】首先利用鲸鱼群算法(WOA)对变分模态分解(VMD)的参数进行优选，实现原始出力序列的最优自适应分解，然后对分解后的每个分量分别建立TCN模型进行趋势预测，最后将所得结果重构得到最终预测结果。【结果】结果显示：与其他模型相比，所提模型在相同条件下预测效果更优。在非汛期，所提模型决定系数R~2为97.08%、平均相对误差MRE为3.68%、均方根误差RMSE为10.05 MW;在汛期，所提模型决定系数R~2为93.71%、平均相对误差MRE为8.09%、均方根误差RMSE为32.96 MW。【结论】结果表明：(1)WOA-VMD方法能够有效地提取径流式水电站出力序列的特征，降低自身数据的不稳定性对预测结果造成的影响；(2)相比于VMD-TCN、TCN、LSTM、RNN、BP五种模型，所提出的WOA-VMD-TCN预测模型能有效提升水电站出力预测精度，为径流式水电站短期出力预测提供了一种新的、有效的建模思路。

关键词(KeyWords)： 径流式水电站;功率预测;鲸鱼群算法;变分模态分解;时间卷积网络;影响因素

Abstract:

Keywords:

基金项目(Foundation): 中国长江电力股份有限公司项目“关联水电站发电能力及蓄能变化趋势研究”(2423020031);; 国家重点研发计划(2018YFB0905204)

作者(Author): 李世林,王李东,刘晓阳,马光文,黄炜斌,朱燕梅

DOI: 10.13928/j.cnki.wrahe.2025.01.016

参考文献(References)：

• [1] 张建云，周天涛，金君良.实现中国“双碳”目标水利行业可以做什么 [J].水利水运工程学报，2022 (1):1-8.ZHANG J Y,ZHOU T T,JIN J L.What can the water conservancy industry do to achieve China’s “dual carbon” goals?[J].Journal of Water Resources and Water Engineering,2022 (1):1-8.
• [2] 白雪.水电在实现“双碳”目标构建新型电力系统中发挥关键作用[N].中国经济导报，2023-08-05(3).BAI X.Hydropower plays a key role in realizing the “dual carbon” goal and building a new power system[N].China Economic Herald,2023-08-05(3).
• [3] 徐玮，罗欣，刘梅，等.用于小水电地区负荷预测的两阶段还原法[J].电网技术，2009,33(8):87-92.XU W,LUO X,LIU M,et al.Two-stage restoration method for load forecasting in small hydropower areas[J].Power System Technology,2009,33(8):87-92.
• [4] 曾洁.小水电发电负荷预测的研究[D].武汉：华中科技大学，2019.ZENG J.Research on Load Forecasting of Small Hydropower Generation[D].Wuhan:Huazhong University of Science and Technology,2019.
• [5] 何勇，李刚，孙永军，等.基于模糊聚类和BP神经网络的小水电短期发电能力预测方法[J].水电能源科学，2014,32(11):188-192.HE Y,LI G,SUN Y J,et al.Short-term generation capacity prediction method for small hydropower based on fuzzy clustering and BP neural network[J].Water Resources and Power,2014,32(11):188-192.
• [6] 刘晨曦，李刚，程春田，等.大小水电相关分析的地区小水电发电能力预测方法[J].水电能源科学，2016,34(8):63-66.LIU C X,LI G,CHENG C T,et al.Regional small hydropower generation capacity prediction method based on correlation analysis of large and small hydropower[J].Water Resources and Power,2016,34(8):63-66.
• [7] 张海锋，杨晶莹，冷俊，等.基于图迁移学习的梯级水电发电超短期预测[J].电网与清洁能源，2023,39(10):104-112.ZHANG H F,YANG J Y,LENG J,et al.Cascaded hydropower generation ultra-short-term forecasting based on graph transfer learning[J].Power Grid and Clean Energy,2023,39(10):104-112.
• [8] KONSTANTINA D K,KONSTANTINA S G,LOANNIS T,et al.Day-ahead energy production in small hydropower plants:Uncertainty-aware forecasts through effective coupling of knowledge and data[J].Advances in Geosciences,2022,56:155-162.
• [9] 张建云，金君良.国家水网建设几个方面问题的讨论[J].水利发展研究，2023,23(11):1-7.ZHANG Jianyun,JIN Junliang.Discussion on several issues concerning the construction of national water network[J].Water Resources Development Research,2023,23(11):1-7.
• [10] 梁曦文，肖峰，闵昊凌，等.基于ESMD-LSSVM模型的径流式水电站出力预测研究[J].中国农村水利水电，2023(9):224-229.LIANG X W,XIAO F,MIN H L,et al.Research on run-of-river hydropower station output prediction based on ESMD-LSSVM model[J].China Rural Water Conservancy and Hydropower,2023(9):224-229.
• [11] 王国娟，冷建伟.基于ESMD-PE和ADBN的短期电力负荷预测[J].电测与仪表，2023,60(1):29-35.WANG G J,LENG J W.Short-term power load forecasting based on ESMD-PE and ADBN[J].Electrical Measurement and Instrumentation,2023,60(1):29-35.
• [12] 刘尚东，孙东永，许晶晶，等.基于ESMD-NNBR耦合的月径流预测模型[J].水文，2023,43(1):52-56.LIU S D,SUN D Y,XU J J,et al.Monthly runoff prediction model based on ESMD-NNBR coupling[J].Hydrology,2023,43(1):52-56.
• [13] 杨健，孙涛，陈小龙，等.基于VMD-EWT-IASSP-EBILSTM的短期电力负荷预测[J].科学技术与工程，2023,23(27):11646-11654.YANG J,SUN T,CHEN X L,et al.Short-term power load forecasting based on VMD-EWT-IASSP-EBILSTM[J].Science Technology and Engineering,2023,23(27):11646-11654.
• [14] 李飞宏，肖迎群.基于VMD-GRU-EC的短期电力负荷预测方法[J].中国测试，2023,49(10):120-127.LI F H,XIAO Y Q.Short-term electricity load forecasting method based on VMD-GRU-EC[J].China Measurement & Testing,2023,49(10):120-127.
• [15] 李昂，张坤，桑宇婷，等.基于ESMD-VMD-ESN二次分解组合模型的水位预测[J].人民珠江，2022,43(11):116-121.LI A,ZHANG K,SANG Y T,et al.Water level prediction based on ESMD-VMD-ESN quadratic decomposition combined model [J].People’s Pearl River,2022,43(11):116-121.
• [16] 李宏扬，高丙朋.基于改进VMD和SNS-Attention-GRU的短期光伏发电功率预测[J].太阳能学报，2023,44(8):292-300.LI H Y,GAO B P.Short-term PV power prediction based on improved VMD and SNS-Attention-GRU[J].Journal of Solar Energy,2023,44(8):292-300.
• [17] 宋绍剑，李博涵.基于LSTM网络的光伏发电功率短期预测方法的研究[J].可再生能源，2021,39(5):594-602.SONG S J,LI B H.Research on short-term forecasting method of photovoltaic power generation based on LSTM network [J].Renewable Energy,2021,39(5):594-602.
• [18] 闫孟婷，黄炜斌，张天遥，等.基于JMI-CNN-LSTM耦合模型的梯级水电站间流量动态滞时关系[J].水利水电技术(中英文),2023,54(3):154-164.YAN M T,HUANG W B,ZHANG T Y,et al.Dynamic lag relationship between inflows of cascade hydropower stations based on JMI-CNN-LSTM coupling model [J].Water Resources and Hydropower Engineering ,2023,54(3):154-164.
• [19] LI D,JIANG F,CHEN M,et al.Multi-step-ahead wind speed forecasting based on a hybrid decomposition method and temporal convolutional networks[J].Energy,2022,238:121981.
• [20] 宋绍剑，姜屹远，刘斌.一种TCN的改进模型及其在短期光伏功率区间预测的应用[J].计算机应用研究，2023,40(10):3064-3069.SONG S J,JIANG Y Y,LIU B.An improved TCN model and its application in short-term PV power interval prediction [J].Applied Research of Computers,2023,40(10):3064-3069.
• [21] 吴珺玥，赵二刚，郭增良，等.基于Spearman系数和TCN的光伏出力超短期多步预测[J].太阳能学报，2023,44(9):180-186.WU J Y,ZHAO E G,GUO Z L,et al.Multi-step ultra-short-term forecasting of photovoltaic output based on Spearman coefficient and TCN[J].Acta Energiae Solaris Sinica,2023,44(9):180-186.
• [22] 马越，温蜜.基于多尺度LDTW和TCN的空间负荷预测方法[J].计算机工程，2024,50 (3):106-113.MA Y,WEN M.Spatial load forecasting based on Multi-scale LDTW and TCN networks [J].Computer Engineering,2024,50 (3):106-113.
• [23] 吴军英，路欣，刘宏，等.基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J].中国电力，2024,57(6):131-140.WU J Y,LU X,LIU H,et al.Super-short-term multi-regional electricity load forecasting based on Spearman-GCN-GRU model [J].China Electric Power,2024,57(6):131-140.
• [24] DRAGOMIRETSKIY K,ZOSSO D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2013,62(3):531-544.
• [25] 陈杨.基于VMD-SSA-BP方法的光伏发电短期功率预测[J].自动化应用，2023,64(15):67-70.CHEN Y.Short-term power prediction of photovoltaic power generation based on VMD-SSA-BP method [J].Automation Applications,2023,64(15):67-70.
• [26] 姜飞，林政阳，王文烨，等.考虑最小平均包络熵负荷分解的最优Bagging集成超短期多元负荷预测[J].中国电机工程学报，2024,44(5):1777-1789.JIANG F,LIN Z Y,WANG W Y,et al.Optimal Bagging ensemble multi-region short-term load forecasting considering minimum mean envelope entropy load decomposition [J].Proceedings of the Chinese Society for Electrical Engineering,2024,44(5):1777-1789.
• [27] MIRJALILI S,LEWIS A.The whale optimization algorithm[J].Advances in Engineering Software,2016,95:51-67.
• [28] 沙金霞.改进鲸鱼算法在多目标水资源优化配置中的应用[J].水利水电技术，2018,49(4):18-26.SHA J X.Application of improved whale algorithm in multi-objective water resource optimization allocation [J].Water Resources and Hydropower Engineering,2018,49(4):18-26.
• [29] 祁宇轩，范俊岩，吴定会，等.基于相似日与BiLSTM组合的短期电力负荷预测[J].控制理论与应用，2024,41(12):2304-2314.QI Y X,FAN J Y,WU D H,et al.Short-term electricity load forecasting based on combined similar days and BiLSTM [J].Control Theory and Applications,2024,41(12):2304-2314.
• [30] BAI S J,KOLTER J Z,KOLTUN V.An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [EB/OL].https://doi.org/10.48550/arXiv.1803.01271.
• [31] 李发崇，李鹏，高莲，等.基于多尺度模型融合和VMD-TCN-RF混合网络的短期电力负荷预测方法[J].电子器件，2023,46(4):1035-1042.LI F C,LI P,GAO L,et al.Short-term electricity load forecasting method based on multiscale model fusion and VMD-TCN-RF hybrid network [J].Electronic Devices,2023,46(4):1035-1042.
• [32] 周业荣，李相锐，绳博宇，等.水风光蓄互补发电系统中风光容量配置研究[J].水利水电技术(中英文),2023,54(11):1-14.ZHOU Y R,LI X R,SHENG B Y,et al.Study on capacity configuration of wind and solar power in complementary generation system for water and hydroelectricity [J].Water Resources and Hydropower Engineering ,2023,54(11):1-14.