胡尧,舒征宇,李黄强,姚钦,李世春,许布哲

• 1:三峡大学电气与新能源学院
• 2:国网宜昌供电公司电网调控中心

摘要(Abstract)：

针对偏远山区径流式小水电发电负荷因来水量不确定性导致预测精度较低的问题，提出一种基于网格化产汇流模型和人工智能的小水电发电负荷预测方法。首先将小水电所在区域进行网格划分，引入径流曲线法(SCS-CN)计算每个网格上的历时降雨产流，再根据单位线原理并结合上游来水量构建小水电区域的网格化产汇流模型。最后，利用卷积神经网络(CNN)对产汇流数据及负荷数据进行高效特征提取，构造双向门控循环单元(BiGRU)网络模型的输入，建立基于降雨产汇流与CNN-BiGRU网络的径流式小水电发电负荷预测模型，通过降低来水量不确定性的影响来提高测试集上预测结果准确率。仿真结果表明，降雨经产汇流模型处理后，小水电发电负荷预测精度提高了7.55%;同时，与单一的GRU网络模型、组合的CNN-GRU网络模型相比，CNN-BiGRU网络模型在测试集上的预测精度分别提高了4.91%、2.39%。综上所述，降雨产汇流模型有效地提高了山区径流式小水电发电负荷的预测精度，为促进富集小水电地区清洁能源的消纳提供了理论依据。

关键词(KeyWords)： 径流式小水电;SCS-CN;卷积神经网络(CNN);BiGRU;负荷预测;降雨;清洁能源;产汇流

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51907104)

作者(Author): 胡尧,舒征宇,李黄强,姚钦,李世春,许布哲

DOI: 10.13928/j.cnki.wrahe.2022.11.014

参考文献(References)：

• [1] 张晶.基于大数据技术的径流式小水电功率预测的研究与应用[D].北京：华北电力大学，2016.ZHANG Jing.Research and application of power prediction of run-of-river small hydropower based on big data technology [D].Beijing:North China Electric Power University,2016.
• [2] 赵爽.计及气象因素的多小水电地区网供负荷预测研究[D].北京：华北电力大学，2018.ZHAO Shuang.Research on network supply of abundant small hydropower load forecast considering meteorological factors [D].Beijing:North China Electric Power University,2018.
• [3] 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.
• [4] CHEND C T,MIAO S M,LUO B,et al.Forecasting monthly energy production of small hydropower plants in ungauged basins using grey model and improved seasonal index [J].Journal of Hydroinformatics,2017,19(6):993-1008.
• [5] NASER A,LIDA R,TIMO P.Effect of land-use change on runoff in Hyrcania [J].Land,2022,11(2) :220-220.
• [6] KISHORE P,RAMESH R,SYED A,et al.A modified distributed CN-VSA method for mapping of the seasonally variable source areas [J].Water,2021,13(9) :1270-1270.
• [7] 王克杰，张瑞.基于改进BP神经网络的短期电力负荷预测方法研究[J].电测与仪表，2019,56(24):115-121.WANG Kejie,ZHANG Rui.Research on short-term power load forecasting method based on improved BP neural network [J].Electrical Measurement & Instrumentation,2019,56(24):115-121.
• [8] 乔石，王磊，张鹏超，等.基于模态分解及注意力机制长短时间网络的短期负荷预测[J/OL].电网技术：1-13[2022-07-20].QIAO Shi,WANG Lei,ZHANG Pengchao,et al.Short-term load forecasting by long and short-term temporal networks with attention based on modal decomposition [J/OL].Power System Technology:1-13 [2022-07-20].
• [9] 肖白，周文凯，姜卓.基于孤立森林、模态分解和神经网络的空间负荷态势感知[J/OL].电力系统自动化：1-11[2022-07-20].XIAO Bai,ZHOU Wenkai,JIANG Zhuo.Space load situational awareness based on isolation forest,mode decomposition and neural network [J/OL].Automation of Electric Power Systems:1-11[2022-07-20].
• [10] 胡昊，马鑫，徐杨，等.基于权重修正和DRSN-LSTM模型的向家坝下游水位多时间尺度预测[J].水利水电技术(中英文),2022,53(7):46-57.HU Hao,MA Xin,XU Yang,et al.Multi-time scale prediction for Xiangjiaba’s downstream water level based on weight correction and DRSN-LSTM model [J].Water Resources and Hydropower Engineering,2022,53(7):46-57.
• [11] ASHRAFUL H,SAIFUR R.Short-term electrical load forecasting through heuristic configuration of regularized deep neural network [J].Applied Soft Computing Journal,2022,122.DOI:10.1016/J.ASOC.2022.108877.
• [12] BENDAOUD N M M,FARAH N,BEN A S.Applying load profiles propagation to machine learning based electrical energy forecasting [J].Electric Power Systems Research,2022,203.DOI:10.1016/J.EPSR.2021.107635.
• [13] KARTHIK S,S,KAVITHAMANI,A.OELF:short term load forecasting for an optimal electrical load forecasting using hybrid whale optimization based convolutional neural network [J].Journal of Ambient Intelligence and Humanized Computing,2021,:1-9.DOI:10.1007/S12652-021-03556-4.
• [14] HOSEIN E,YUDHO Y,CANAS R P.The use of singular spectrum analysis and K-Means clustering-based bootstrap to improve multistep ahead load forecasting [J].Energies,2022,15(16) :5838-5838.
• [15] WINITA S,MARYAM I,PARSA M M.Convolutional and recurrent neural network based model for short-term load forecasting [J].Electric Power Systems Research,2021,195.DOI:10.1016/J.EPSR.2021.107173.
• [16] 洪林，罗琳，江海涛.SCS模型在流域尺度水文模拟中的应用[J].武汉大学学报(工学版),2009,42(5):582-586.HONG Lin,LUO Lin,JIANG Haitao.Application of SCS model to hydrological simulation at an agricultural watershed scale [J].Engineering Journal of Wuhan University,2009,42(5):582-586.
• [17] 吴艾璞，王晓燕，黄洁钰，等.基于前期雨量和降雨历时的SCS-CN模型改进[J].农业工程学报，2021,37(22):85-94.WU Aipu,WANG Xiaoyan,HUANG Jieyu,et al.Improvement of SCS-CN model based on antecedent precipitation and rainfall duration [J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(22):85-94.
• [18] 许秀泉，范昊明，李刚.径流曲线法在东北半干旱区几种土地利用方式径流估算中的应用与改正[J].水土保持学报，2019,33(4):52-57.XU Xiuquan,FAN Haoming,LI Gang.Application and several correction of the SCS-CN method in runoff estimation of land use patterns in northeast semi-arid region [J].Journal of Soil and Water Conservation,2019,33(4):52-57.
• [19] 赵登良，陈振江，刘建华，等.SCS-CN模型在济南市南部山区径流估算中的优化应用[J].南水北调与水利科技(中英文),2022,20(2):308-316.ZHAO Dengliang,CHEN Zhenjiang,LIU Jianhua,et al.Optimal application of SCS-CN model in runoff estimation in the southern mountainous area of Jinan [J].South-to-North Water Transfers and Water Science & Technology,2022,20(2):308-316.
• [20] FENG M L,ZHANG T G,LI S C,et al.An improved minimum bounding rectangle algorithm for regularized building boundary extraction from aerial LiDAR point clouds with partial occlusions [J].International Journal of Remote Sensing,2020,41(1) :300-319.
• [21] 万晓丹，曹京京，申红彬.Clark单位线法的分布式改进[J].长江科学院院报，2018,35(5):23-26.WAN Xiaodan,CAO Jingjing,SHEN Hongbin.Improvement of clark unit hydrograph to distributed unit hydrograph model [J].Journal of Yangtze River Scientific Research,2018,35(5):23-26.
• [22] 魏道红，王博，张明.基于CNN的混凝土坝变形预测深度学习模型研究[J].水利水电技术(中英文),2021,52(6):52-57.WEI Daohong,WANG Bo,ZHANG Ming.A deep learning model for concrete dam deformation prediction based on CNN [J].Water Resources and Hydropower Engineering,2021,52(6):52-57.
• [23] 邵必林，严义川，曾卉玢.注意力机制下的VMD-IDBiGRU负荷预测模型[J/OL].电力系统及其自动化学报：1-7[2022-07-20].SHAO Bilin,YAN Yichuan,ZENG Huiping.VMD-IDBiGRU load prediction model under attentional mechanism [J/OL].Proceedings of the CSU-EPSA:1-7[2022-07-20].
• [24] MENG Y Y,CHANG C,HUO J Y,et al.Research on ultra-short-term prediction model of wind power based on attention mechanism and CNN-BiGRU combined [J].Frontiers in Energy Research,2022.DOI:10.3389/FENRG.2022.920835.