| 176 | 2 | 469 |
| 下载次数 | 被引频次 | 阅读次数 |
【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R2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R2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。
Abstract：[Objective]Accurate power prediction of a runoff hydropower station is crucial for formulating generation scheduling plans and ensuring a reliable power supply strategy. Considering the strong randomness in the generation output of runoff hydropower stations and the low accuracy of direct prediction, a combined prediction model based on Adaptive Variational Mode Decomposition(VMD) and Temporal Convolutional Network(TCN) was proposed.[Methods]Initially, the Whale Optimization Algorithm(WOA) is employed to optimize the parameters of Variational Mode Decomposition(VMD), achieving optimal adaptive decomposition of the original output sequence. Subsequently, TCN model is individually established for trend prediction of each decomposed component. Finally, the obtained result are reconstructed to obtain the final prediction.[Results]The result shows that, compares to other models, the model established has varying degrees of improvement in prediction performance under the same conditions.[Conclusion]The result indicates:(1) The WOA-VMD method can effectively extract the characteristics of the output sequence of a runoff-type hydropower station and reduce the influence of the instability of its own data on the prediction result.(2) Compared to the five models of VMD-TCN, TCN, LSTM, RNN and BP, the proposed WOA-VMD-TCN prediction model can effectively improve the prediction accuracy of hydropower station power, providing a new and effective modeling approach for power prediction of runoff hydropower stations.
[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.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.01.016
中图分类号:TV747
引用信息:
[1]李世林,王李东,刘晓阳,等.径流式水电站出力预测的学习模型研究[J].水利水电技术(中英文),2025,56(01):193-202.DOI:10.13928/j.cnki.wrahe.2025.01.016.
基金信息:
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)
2023-12-18
2023
2024-11-09
2024
2
2025-01-20
2025-01-20