您好,欢迎来到中国测试科技资讯平台!

首页> 数字期刊群 >本期导读>CEEMD双层分解和Granger因果变量选择风电功率预测

CEEMD双层分解和Granger因果变量选择风电功率预测

435    2023-08-15

免费

全文售价

作者:刘勇1, 杨熙卉2, 燕林滋1, 欧云1

作者单位:1. 银川能源学院,宁夏 银川 750100;
2. 宁夏交通学校,宁夏 银川 750200


关键词:风电功率预测;完备集成经验模态分解;长短时记忆网络;Granger因果关系检验


摘要:

针对风电功率时间序列具有高度随机波动性而无法精准预测的问题,提出一种基于完备集成经验模态分解(CEEMD)、Granger因果关系检验和长短时记忆网络的新型混合预测方法用于预测风电功率。首先,为研究风电功率和风速的隐性相关性,通过CEEMD算法对风电功率和风速时间序列分别进行序列分解,实现双层分解。其次,通过Granger因果关系方法对各风速分量与各风电功率分量进行因果关系检验,分析风电功率分量与各风速分量间的相关性,以此实现各风电功率分量的输入变量选择。最后,采用长短时记忆网络对各风电功率分量进行预测,并集成得到最终的风电功率预测结果。通过风电厂的实际数据进行了试验,并与多个应用广泛的经典模型进行对比,结果表明该方法的预测精度取得了大幅度提高,能够对风电功率实现精准预测。


Wind power prediction based on CEEMD and Granger causality variable selection
LIU Yong1, YANG Xihui2, YAN Linzi1, OU Yun1
1. Yinchuan Energy Institute, Yinchuan 750100, China;
2. Ningxia Transportation School, Yinchuan 750200, China
Abstract: Due to the high random fluctuation of wind power time series, a hybrid prediction method based on CEEMD, Granger causality test and LSTM was proposed to predict wind power. Firstly, the wind power and wind speed time series are decomposed respectively through CEEMD to achieve the two-layer decomposition. Secondly, the Granger causality method is used to test the causality between each wind speed component and each wind power component, so as to realize the selection of input variables. Finally, LSTM is used to predict each wind power component. The final predicted value of wind power is obtained through integration to build a complete wind power prediction model. The actual data of wind power plants were tested and compared with several widely used classical models. The results show that the prediction accuracy of this method has been greatly improved, and the accurate prediction of wind power can be realized.
Keywords: wind power prediction;CEEMD;LSTM;Granger causality test
2023, 49(4):98-105  收稿日期: 2021-07-21;收到修改稿日期: 2021-10-26
基金项目: 宁夏自然科学基金项目(2021AAC03254);宁夏高等学校科学研究项目(NGY2020123)
作者简介: 刘勇(1986-),男,讲师,硕士,主要从事计算机控制、电气工程与控制研究
参考文献
[1] 朱瑞金, 龚雪娇, 张娟娟. 基于EEMD-MPE-LSSVM的光伏发电功率预测[J]. 中国测试, 2021, 47(9): 158-162
[2] AOIFE M, PAUL G, MARVUGLIA A, et al. Current methods and advances in forecasting of wind power generation[J]. Renewable Energy, 2012, 37(1): 1-8
[3] ASIYE K, YAPRAKDAL, MUSTAFA B. Deep learning methods and applications for electrical power systems: A comprehensive review[J]. International Journal of Energy Research, 2020, 44(9): 7136-7157
[4] 黎静华, 桑川川, 甘一夫, 等. 风电功率预测技术研究综述[J]. 现代电力, 2017, 34(3): 1-11
[5] 岳勇, 陈雯婷, 聂伟. LMD和ARMA组合风速预测方法[J]. 中国测试, 2020, 46(8): 126-130
[6] 杨茂, 董昊. 基于风速分频和权值匹配的RBF超短期风电功率预测方法[J]. 可再生能源, 2020, 38(11): 1483-1488
[7] 梅雨, 王红蕾, 王瑾. 基于PSO-BP组合改进模型的短期风电功率预测仿真[J]. 软件, 2020, 41(12): 7-10
[8] 孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(04): 1129-1143
[9] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802
[10] 王涛, 高靖, 王优胤, 等. 基于改进经验模态分解和支持向量机的风电功率预测研究[J]. 电测与仪表, 2021, 58(06): 49-54
[11] ZHANG Y, HAN J, PAN G, et al. A multi-stage predicting methodology based on data decomposition and error correction for ultra-short-term wind energy prediction[J]. Journal of Cleaner Production, 2021, 292: 19
[12] 刘亚珲, 赵倩. 基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测[J]. 电网技术: 1-8.
[13] WU Z, NORDEN E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41
[14] 杨茂, 王凯旋. 基于CEEMD-DBN模型的光伏出力日前区间预测[J]. 高电压技术, 2021, 47(4): 1156-1164