人为设定白噪声的幅值和加噪次数及白噪声自身的随机性会对集合经验模态分解（EEMD）方法的分解结果造成不确定性,导致EEMD应用于风功率预测时不能实现最佳的分解效果。该文研究了白噪声参数对EEMD分解效果的影响机理,并提出基于分形特征的自适应EEMD方法。在不同的白噪声及白噪声参数下, EEMD分解所得到的模态分量具有不同的分形维特征,采用粒子群算法寻优获得EEMD处理某一信号的最佳参数,实现对信号的准确分解。同时结合具有良好非线性建模能力的长短时记忆（LSTM）网络方法对自适应EEMD分解得到的模态分量进行预测,利用仿真信号及两个风电场实际风功率数据进行分析,自适应EEMD避免了白噪声的随机性及人为设定参数对EEMD分解结果带来的不确定性影响。与3种基准预测模型对比,自适应EEMD结合LSTM模型预测两组风功率的RMSE显著降低,验证了该文研究方法的有效性。
Abstract
Artificially given amplitude and ensemble number of white noises and the randomness of white noises causes the uncertainty to the decomposed results of ensemble empirical mode decomposition （EEMD）, leading to the imperfect decomposed results in application to the wind power prediction by EEMD. The effect mechanism of the parameters of white noises on decomposed results of EEMD is studied, and the method called adaptive EEMD based on fractal characteristics of modes is proposed in this paper. In the different white noises and different parameters of white noises, the modes decomposed by EEMD exhibit the different fractal characteristics. Particle swarm optimization algorithm is adopted to calculate the fractal dimensions of modes in different parameters, so as to achieve the precise decomposition for EEMD. Employing long short term memory （LSTM） algorithm which has great nonlinear modeling ability to predict decomposed components obtained by adaptive EEMD. Simulated signal and actual wind power data from two wind farms are analyzed. Adaptive EEMD could avoid the uncertainty brought by the randomness of white noises and artificially given parameters. Compared with three benchmark models, the RMSE is significantly reduced by adaptive EEMD combined with LSTM model on two groups of wind power data, which verifies the effectiveness of the proposed method.
关键词
分形维数 /
风功率 /
长短时记忆网络 /
自适应EEMD
Key words
fractal dimension /
wind power /
long short-term memory /
adaptive EEMD
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 凡航, 张雪敏, 梅生伟, 等. 基于时空神经网络的风电场超短期风速预测模型[J]. 电力系统自动化, 2021, 45(1): 28-35.
FAN H, ZHANG X M, MEI S W, et al.Ultra-short-term wind speed prediction model for wind farms based on spatiotemporal neural network[J]. Automation of electric power systems, 2021, 45(1): 28-35.
[2] 栗然, 马涛, 张潇, 等. 基于卷积长短期记忆神经网络的短期风功率预测[J]. 太阳能学报, 2021, 42(6): 304-311.
LI R, MA T, ZHANG X, et al.Short-term wind power prediction based on convolutional long-short-term memory neural networks[J]. Acta energiae solaris sinica, 2021, 42(6): 304-311.
[3] 金吉, 王斌, 喻敏, 等. Lorenz方程优化EMD分解过程的短期风速预测[J]. 太阳能学报, 2021, 42(6): 342-348.
JIN J, WANG B, YU M, et al.Short-term wind speed prediction based on EMD optimized by Lorenz equation[J]. Acta energiae solaris sinica, 2021, 42(6): 342-348.
[4] 梁超, 刘永前, 周家慷, 等. 基于卷积循环神经网络的风电场内多点位风速预测方法[J]. 电网技术, 2021, 45(2): 534-541.
LIANG C, LIU Y Q, ZHOU J K, et al.Wind speed prediction at multi-locations based on combination of recurrent and convolutional neural networks[J]. Power system technology, 2021, 45(2): 534-541.
[5] 谢丽蓉, 王斌, 包洪印, 等. 基于EEMD-WOA-LSSVM的超短期风电功率预测[J]. 太阳能学报, 2021, 42(7): 290-296.
XIE L R, WANG B, BAO H Y, et al.Super-short-term wind power forecasting based on EEMD-WOA-LSSVM[J]. Acta energiae solaris sinica, 2021, 42(7): 290-296.
[6] YC A, ZD A, YAN W A, et al.Short-term wind speed predicting framework based on EEMD-GA-LSTM method under large scaled wind history[J]. Energy conversion and management, 2021, 227: 1-16.
[7] HU H L, WANG L, TAO R.Wind speed forecasting based on variational mode decomposition and improved echo state network[J]. Renewable energy, 2021, 164: 729-751.
[8] YEH J R, SHIEH J S, HUANG N E.Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method[J]. Advances in adaptive data analysis, 2010, 2(2): 135-156.
[9] ZHENG J D, CHENG J S, YANG Y.Partly ensemble empirical mode decomposition:an improved noise-assisted method for eliminating mode mixing[J]. Signal processing, 2014, 96: 362-374.
[10] 郑近德, 程军圣, 杨宇. 改进的EEMD算法及其应用研究[J]. 振动与冲击, 2013, 32(21): 21-26.
ZHENG J D, CHENG J S, YANG Y.Modified EEMD algorithm and its applications[J]. Journal of vibration and shock, 2013, 32(21): 21-26.
[11] REN Y, SUGANTHAN P N, SRIKANTH N.A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods[J]. IEEE transactions on sustainable energy, 2017, 6(1): 236-244.
[12] 赵征, 汪向硕. 基于CEEMD和改进时间序列模型的超短期风功率多步预测[J]. 太阳能学报, 2020, 41(7): 352-358.
ZHAO Z, WANG X S.Ultra-short-term multi-step wind power prediction based on CEEMD and improved time series model[J]. Acta energiae solaris sinica, 2020, 41(7): 352-358.
[13] WU Z, HUANG N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in adaptive data analysis, 2011, 1(1): 1-41.
[14] JIN J, WANG B, YU M, et al.A novel self-adaptive wind speed prediction model considering atmospheric motion and fractal feature[J]. IEEE access, 2020(8): 215892-215903.
[15] SU Z Y, WANG J Z, LU H Y, et al.A new hybrid model optimized by an intelligent optimization algorithm for wind speed forecasting[J]. Energy conversion and management, 2014, 85: 443-452.
[16] SEPP H, JÜRGEN S. Long short-term memory[J]. Journal of neural computation, 1997, 9(8):1735-1780.
[17] WANG S X, ZHANG N, WU L, et al.Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method[J]. Renewable energy, 2016, 94(8): 629-636.
[18] 茆美琴, 龚文剑, 张榴晨, 等. 基于EEMD-SVM方法的光伏电站短期出力预测[J]. 中国电机工程学报, 2013, 33(34): 17-24.
MAO M Q, GONG W J, ZHANG L C, et al.Short-term photovoltaic generation forecasting based on EEMD-SVM combined method[J]. Proceedings of the CSEE, 2013, 33(34): 17-24.
[19] 张群, 唐振浩, 王恭, 等. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G, et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
PDF(1826 KB)
