The hybrid of wavelet packet decomposition and machine learning models in wind speed forecasting

doi:10.7522/j.issn.1000-694X.2020.00124

Journal of Desert Research ›› 2021, Vol. 41 ›› Issue (2): 38-50.DOI: 10.7522/j.issn.1000-694X.2020.00124

Previous Articles Next Articles

The hybrid of wavelet packet decomposition and machine learning models in wind speed forecasting

Tongliang Wang¹^,³(), Shaoxiu Ma¹(), Yang Gao¹^,³, Yulai Gong¹^,³, Zhishan An²

^1.Key Laboratory of Desert and Desertification /, Northwest Institute of Eco-Environment and Resources，Chinese Academy of Sciences，Lanzhou 730000，China
^2.Public Technical Service Center, Northwest Institute of Eco-Environment and Resources，Chinese Academy of Sciences，Lanzhou 730000，China
^3.University of Chinese Academy of Sciences，Beijing 100049，China

Received:2020-10-08 Revised:2020-12-04 Online:2021-03-20 Published:2021-03-26
Contact: Shaoxiu Ma

Abstract

Abstract:

Wind speed forecasting is an effective method to improve wind power utilization and power system stability. Previous studies proposed a amount of wind speed forecast models， but there are few comparative studies on wind speed forecast models for different underlying land cover. This study mainly explores the ability of wavelet packet decomposition， 12 machine learning models and their coupled models to forecast the wind speed for three different underlying land cover and landforms （gobi， oasis and desert）， and explores the optimized coupled model for wind speed forecast. Three sets of model experiments were set up for comparison in the article： single XXX model， WPD-XXX hybrid model and WPD-XXX-CNN hybrid model. We found that the deep learning models with feature selection， memory functions （such as convolutional long short-term memory networks） and extreme learning machine have better forecast capabilities for wind speed forecast. The wavelet packet decomposition significantly improves model accuracy. The coupled modesl of wavelet packet decomposition and convolutional long short-term memory network， convolutional gated recurrent unit network has better performance. This shows that the use of signal decomposition and the coupling of deep learning models can effectively improve the forecast accuracy of the models. It could be widely used in industry practices.

Key words: wind speed forecast, wavelet packet decomposition, deep learning model, arid and semi-arid area, hybrid model

CLC Number:

P425.63

Tongliang Wang, Shaoxiu Ma, Yang Gao, Yulai Gong, Zhishan An. The hybrid of wavelet packet decomposition and machine learning models in wind speed forecasting[J]. Journal of Desert Research, 2021, 41(2): 38-50.

Figures/Tables 11

References 36

1	Liu M S，Cao Z M，Zhang J，et al.Short-term wind speed forecasting based on the Jaya-SVM model［J］.International Journal of Electrical Power & Energy Systems，2020，121：106056.
2	王俊，李霞，周昔东，等.基于VMD和LSTM的超短期风速预测［J］.电力系统保护与控制，2020，48（11）：45-52.
3	张丽英，叶廷路，辛耀中，等.大规模风电接入电网的相关问题及措施［J］.中国电机工程学报，2010，30（25）：1-9.
4	Liu H，Mi X W，Li Y F.Comparison of two new intelligent wind speed forecasting approaches based on wavelet packet decomposition，complete ensemble empirical mode decomposition with adaptive noise and artificial neural networks［J］.Energy Conversion and Management，2018，155：188-200.
5	Dong Q L，Sun Y H，Li P Z.A novel forecasting model based on a hybrid processing strategy and an optimized local linear fuzzy neural network to make wind power forecasting：a case study of wind farms in China［J］.Renewable Energy，2017，102：241-257.
6	Howard T，Clark P.Correction and downscaling of NWP wind speed forecasts［J］.Meteorological Applications，2007，14（2）：105-116.
7	黄彦辉，王龙杰，杨薛明.基于混沌时间序列的支持向量机短期风速预测模型研究［J］.电测与仪表，2015，52（17）：32-37.
8	李应求，安勃，李恒通.基于NARX及混沌支持向量机的短期风速预测［J］.电力系统保护与控制，2019，47（23）：65-73.
9	梁智，孙国强，俞娜燕，等.基于高斯过程回归和粒子滤波的短期风速预测［J］.太阳能学报，2020，41（3）：45-51.
10	喻敏，常毓婵，袁浩，等.基于HP-EMD和ARMA的短期风速预测［J］.中国科技论文，2016，11（5）：566-570.
11	孙驷洲，陈亮，郭兴众，等.基于EEMD与极限学习机的短期风速组合预测模型［J］.安徽工程大学学报，2018，33（4）：56-63.
12	王晨，寇鹏.基于卷积神经网络和简单循环单元集成模型的风电场内多风机风速预测［J］.电工技术学报，2020：1-14.
13	Yu C J，Li Y L，Xiang H Y，et al.Data mining-assisted short-term wind speed forecasting by wavelet packet decomposition and elman neural network［J］.Journal of Wind Engineering and Industrial Aerodynamics，2018，175：136-143.
14	Harbola S，Coors V.One dimensional convolutional neural network architectures for wind prediction［J］.Energy Conversion and Management，2019，195：70-75.
15	Liu H，Tian H Q，Li Y F.Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms［J］.Energy Conversion and Management，2015，100：16-22.
16	Hao Y，Tian C S.A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting［J］.Applied Energy，2019，238：368-383.
17	Liu H，Tian H Q，Liang X F，et al.Wind speed forecasting approach using secondary decomposition algorithmn and elman neural networks［J］.Applied Energy，2015，157：183-194.
18	Pei S Q，Qin H，Zhang Z，et al.Wind speed prediction method based on empirical wavelet transform and new cell update long short-term memory network［J］.Energy Conversion and Management，2019，196：779-792.
19	叶瑞丽，郭志忠，刘瑞叶，等.基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测［J］.电工技术学报，2017，32（21）：103-111.
20	王宁，罗汝斌，廖俊，等.基于小波包分解的BP神经网络的短期风速预测［J］.控制与信息技术，2019（4）：44-49.
21	Mi X W，Liu H，Li Y F.Wind speed forecasting method using wavelet，extreme learning machine and outlier correction algorithm［J］.Energy Conversion and Management，2017，151：709-722.
22	Liu H，Yu C Q，Wu H P，et al.A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting［J］.Energy，2020，202：1-36.
23	Moreno S R，Silva R G D，Mariani V C，et al.Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network［J］.Energy Conversion and Management，2020，213：112869.
24	Mi X W，Liu H，Li Y F.Wind speed prediction model using singular spectrum analysis，empirical mode decomposition and convolutional support vector machine［J］.Energy Conversion and Management，2019，180：196-205.
25	Feng C，Cui M J，Hodge B M，et al.A data-driven multi-model methodology with deep feature selection for short-term wind forecasting［J］.Applied Energy，2017，190：1245-1257.
26	Liu H，Mi X W，Li Y F.An experimental investigation of three new hybrid wind speed forecasting models using multi-decomposing strategy and ELM algorithm［J］.Renewable Energy，2018，123：694-705.
27	Liu H，Mi X W，Li Y F.Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition，singular spectrum analysis，LSTM network and ELM［J］.Energy Conversion and Management，2018，159：54-64.
28	Liu H，Mi X W，Li Y F.Smart deep learning based wind speed prediction model using wavelet packet decomposition，convolutional neural network and convolutional long short term memory network［J］.Energy Conversion and Management，2018，166：120-131.
29	Ding L Y，Fang W L，Luo H B，et al.A deep hybrid learning model to detect unsafe behavior：integrating convolution neural networks and long short-term memory［J］.Automation in Construction，2018，86：118-124.
30	Memarzadeh G，Keynia F.A new short-term wind speed forecasting method based on fine-tuned LSTM neural network and optimal input sets［J］.Energy Conversion and Management，2020，213：112824.
31	Li Y F，Shi H P，Han F Z，et al.Smart wind speed forecasting approach using various boosting algorithms，big multi-step forecasting strategy［J］.Renewable Energy，2019，135：540-553.
32	Zhang Y G，Pan G F，Chen B，et al.Short-term wind speed prediction model based on GA-ANN improved by VMD［J］.Renewable Energy，2020，156：1373-1388.
33	Zhang J L，Wei Y M，Tan Z F.An adaptive hybrid model for short term wind speed forecasting［J］.Energy，2019，190：115615.
34	Hao Y，Tian C.A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting［J］.Applied Energy，2019，238：368-383.
35	Ghimire S，Deo R C，Raj N，et al.Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms［J］.Applied Energy，2019，253：113541.
36	Liu H，Mi X W，Li Y F，et al.Smart wind speed deep learning based multi-step forecasting model using singular spectrum analysis，convolutional gated recurrent unit network and support vector regression［J］.Renewable Energy，2019，143：842-854.

模型	英文名称（缩写）
支持向量回归	Support Vector Regression（SVR）
梯度提升回归	Gradient Boosting Regression（GBR）
随机森林	Random Forest（RF）
人工神经网络	Artificial Neural Network（ANN）
极限学习机	Extreme Learning Machine（ELM）
卷积神经网络	Convolutional Neural Network（CNN）
长短时记忆网络	Long Short-term Memory（LSTM）
堆叠式长短时记忆网络	Stacked Long Short-term Memory（SLSTM）
双向长短时记忆网络	Bidirectional Long Short-term Memory（BLSTM）
门控循环单元	Gated Recurrent Unit（GRU）
卷积长短时记忆网络	Convolutional Long Short-term Memory（CLSTM）
卷积门控循环单元	Convolutional Gated Recurrent Unit（CGRU）

模型	英文名称（缩写）
支持向量回归	Support Vector Regression（SVR）
梯度提升回归	Gradient Boosting Regression（GBR）
随机森林	Random Forest（RF）
人工神经网络	Artificial Neural Network（ANN）
极限学习机	Extreme Learning Machine（ELM）
卷积神经网络	Convolutional Neural Network（CNN）
长短时记忆网络	Long Short-term Memory（LSTM）
堆叠式长短时记忆网络	Stacked Long Short-term Memory（SLSTM）
双向长短时记忆网络	Bidirectional Long Short-term Memory（BLSTM）
门控循环单元	Gated Recurrent Unit（GRU）
卷积长短时记忆网络	Convolutional Long Short-term Memory（CLSTM）
卷积门控循环单元	Convolutional Gated Recurrent Unit（CGRU）

观测点	时间范围	时间分辨率/min	高度/m
戈壁（40.5593°N、93.1117°E）	2019年4月21日20:40—26日17:10	10	10
绿洲（40.2581°N、94.7551°E）	2018年12月1日21:20—6日17:50	10	10
沙漠（40.0082°N、94.5940°E）	2019年5月21日00:40—25日21:10	10	10

观测点	时间范围	时间分辨率/min	高度/m
戈壁（40.5593°N、93.1117°E）	2019年4月21日20:40—26日17:10	10	10
绿洲（40.2581°N、94.7551°E）	2018年12月1日21:20—6日17:50	10	10
沙漠（40.0082°N、94.5940°E）	2019年5月21日00:40—25日21:10	10	10

模型	戈壁			绿洲			沙漠
模型	单一XXX模型	WPD-XXX混合模型	WPD-XXX-CNN模型	单一XXX模型	WPD-XXX混合模型	WPD-XXX-CNN模型	单一XXX模型	WPD-XXX混合模型	WPD-XXX-CNN模型
SVR	0.8468	0.9520	0.9607	0.8682	0.9322	0.9459	0.1532	0.5506	0.5952
RF	0.8356	0.9706	0.9803	0.8460	0.9763	0.9846	0.3740	0.8827	0.8989
GBR	0.8311	0.9674	0.9726	0.8221	0.9824	0.9866	0.3243	0.8798	0.8935
ANN	0.8491	0.9700	0.9714	0.8692	0.9841	0.9834	0.5360	0.9372	0.9261
ELM	0.8329	0.9922	0.9943	0.8762	0.9967	0.9953	0.5276	0.9792	0.9754
CNN	0.8287	0.9571	0.9571	0.8864	0.9919	0.9919	0.4916	0.9349	0.9349
LSTM	0.8694	0.9725	0.9753	0.8852	0.9799	0.9788	0.5678	0.9369	0.9345
SLSTM	0.8533	0.9698	0.9660	0.8797	0.9862	0.9858	0.4360	0.9719	0.9588
BLSTM	0.8655	0.9641	0.9623	0.8924	0.9849	0.9873	0.5390	0.8950	0.9105
GRU	0.8627	0.9870	0.9888	0.8902	0.9918	0.9911	0.5674	0.9496	0.9449
CLCTM	0.8568	0.9931	0.9942	0.8719	0.9921	0.9923	0.4557	0.9308	0.9315
CGRU	0.8579	0.9933	0.9931	0.8796	0.9922	0.9914	0.4534	0.9461	0.9433
A3	0.8704	0.9953	0.9942	0.8923	0.9953	0.9945	0.5837	0.9714	0.9633
A12	0.8693	0.9896	0.9891	0.8891	0.9937	0.9932	0.5047	0.9311	0.9289

The hybrid of wavelet packet decomposition and machine learning models in wind speed forecasting

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 36

Related Articles 2

Recommended Articles

Metrics

Comments

[1]	Xueshang Chang, Guoqiao Chang. Advances in research and prospect on soil moisture in arid and semi-arid areas [J]. Journal of Desert Research, 2021, 41(1): 156-163.
[2]	LI Jing, SUN Hu, XING Dong-xing, WANG Xiang-ge. Characteristics of Wetland and Its Conservation in Arid and Semi-arid Areas in Northwest of China [J]. JOURNAL OF DESERT RESEARCH, 2003, 23(6): 670-674.