为了提升短期风速预测的准确性,提出一种新型的短期风速预测方法。该方法以历史风速和气象数据作为输入,首先利用特征选择网络量化输入序列中每个时间步不同特征的重要程度,其次采用多尺度因果卷积网络捕捉其局部时序特征,然后引入自注意力融合不同卷积层的特征,得到能反映风速多尺度变化特性的高维特征序列,最后利用双向长短期记忆网络提取高维特征序列的长期时序特征并得到风速预测结果。实验结果表明,该方法能考虑不同输入特征对于风速的动态影响,同时充分提取风速序列的局部与长期时序特征,其进行提前1 h的风速预测时,所得归一化均方根误差与平均绝对误差分别为11.92%和8.11%,相关系数和决定系数分别为0.9735和0.9477,可有效提高短期风速预测的准确性。
Abstract
In order to improve the short-term wind speed prediction acccuracy, a novel wind speed forecasting method is proposed. This method uses historical wind speed and meteorological data as inputs and first utilizes feature selection networks to quantify the importance of different features at each time step in the input sequence. Local temporal features are then captured by the multi-scale causal convolutional network. After that, self attention is introduced to integrate features from different convolutional layers, generating a high-dimensional feature sequence which can reflect multi-scale characteristics of the wind speed. Finally, BiLSTM is used to extract long-term temporal features of the high-dimensional feature sequence to obtain forecasting results of wind speed. Experimental results demonstrate that the proposed method can consider the dynamic effects of different input features on wind speed and fully extract both local and long-term temporal features of the wind speed sequence. The normalized root mean square error and mean absolute error of the proposed model for one-hour ahead wind speed forecasting are 11.92% and 8.11%, respectively. The proposed method also achieves a high prediction accuracy with correlation coefficient of 0.9735 and coefficient of determination of 0.9477, which improves the accuracy of short-term wind speed forecasting effectively.
关键词
风力发电 /
风速 /
预测 /
特征选择 /
深度学习 /
自注意力
Key words
wind power /
wind speed /
forecasting /
feature selection /
deep learning /
self attention
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] CHENG L L, ZANG H X, XU Y, et al.Augmented convolutional network for wind power prediction: a new recurrent architecture design with spatial-temporal image inputs[J]. IEEE transactions on industrial informatics, 2021, 17(10): 6981-6993.
[2] 吴浩天, 孙荣富, 廖思阳, 等. 基于改进气象聚类分型的短期风电功率概率预测方法[J]. 电力系统自动化, 2022, 46(15): 56-65.
WU H T, SUN R F, LIAO S Y, et al.Short-term wind power probability forecasting method based on improved meteorological clustering and classification[J]. Automation of electric power systems, 2022, 46(15): 56-65.
[3] 赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Z N, YUN S N, JIA L Y, et al.Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta energiae solaris sinica, 2022, 43(11): 224-234.
[4] ZHAO Z N, YUN S N, JIA L Y, et al.Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features[J]. Engineering applications of artificial intelligence, 2023, 121: 105982.
[5] WANG Y, ZOU R M, LIU F, et al.A review of wind speed and wind power forecasting with deep neural networks[J]. Applied energy, 2021, 304: 117766.
[6] 关永锋, 喻敏, 胡佳. 基于自适应组合模型的超短期风速预测[J]. 电力系统保护与控制, 2022, 50(4): 120-128.
GUAN Y F, YU M, HU J.Ultra-short-term wind speed prediction based on an adaptive integrated model[J]. Power system protection and control, 2022, 50(4): 120-128.
[7] 赵鑫, 陈臣鹏, 毕贵红, 等. 基于PAM-SSD-LSTM的短期风速预测[J]. 太阳能学报, 2023, 44(1): 281-288.
ZHAO X, CHEN C P, BI G H, et al.Short-term wind speed prediction based on PAM-SSD-LSTM[J]. Acta energiae solaris sinica, 2023, 44(1): 281-288.
[8] LI Y M, PENG T, ZHANG C, et al.Multi-step ahead wind speed forecasting approach coupling maximal overlap discrete wavelet transform, improved grey wolf optimization algorithm and long short-term memory[J]. Renewable energy, 2022, 196: 1115-1126.
[9] JOSEPH L P, DEO R C, PRASAD R, et al.Near real-time wind speed forecast model with bidirectional LSTM networks[J]. Renewable energy, 2023, 204: 39-58.
[10] 修春波, 苏欢, 苏雪苗. 多通道长短期记忆卷积网络的风速预测[J]. 电力工程技术, 2022, 41(1): 64-69.
XIU C B, SU H, SU X M.Wind speed prediction based on multi-channel long short-term memory convolution neural network[J]. Electric power engineering technology, 2022, 41(1): 64-69.
[11] 毕贵红, 赵鑫, 李璐, 等. 双模式分解CNN-LSTM集成的短期风速预测模型[J]. 太阳能学报, 2023, 44(3): 191-197.
BI G H, ZHAO X, LI L, et al.Dual-mode decomposition CNN-LSTM integrated short-term wind speed forecasting model[J]. Acta energiae solaris sinica, 2023, 44(3): 191-197.
[12] CHEN J, LIU H, CHEN C, et al.Wind speed forecasting using multi-scale feature adaptive extraction ensemble model with error regression correction[J]. Expert systems with applications, 2022, 207: 117358.
[13] SHANG Z H, CHEN Y, CHEN Y H, et al.Decomposition-based wind speed forecasting model using causal convolutional network and attention mechanism[J]. Expert systems with applications, 2023, 223: 119878.
[14] 刘擘龙, 张宏立, 王聪, 等. 基于序列到序列和注意力机制的超短期风速预测[J]. 太阳能学报, 2021, 42(9): 286-294.
LIU B L, ZHANG H L, WANG C, et al.Ultra-short-term wind speed prediction based on sequence-to-sequence and attention mechanism[J]. Acta energiae solaris sinica, 2021, 42(9): 286-294.
[15] ZOU R M, SONG M M, WANG Y, et al.Deep non-crossing probabilistic wind speed forecasting with multi-scale features[J]. Energy conversion and management, 2022, 257: 115433.
[16] WU J, LI N, ZHAO Y, et al.Usage of correlation analysis and hypothesis test in optimizing the gated recurrent unit network for wind speed forecasting[J]. Energy, 2022, 242: 122960.
[17] WANG J Z, LYU M Z, LI Z W, et al.Multivariate selection-combination short-term wind speed forecasting system based on convolution-recurrent network and multi-objective chameleon swarm algorithm[J]. Expert systems with applications, 2023, 214: 119129.
[18] LYU S X, WANG L.Multivariate wind speed forecasting based on multi-objective feature selection approach and hybrid deep learning model[J]. Energy, 2023, 263: 126100.
[19] LIM B, ARıK S Ö, LOEFF N, et al. Temporal Fusion Transformers for interpretable multi-horizon time series forecasting[J]. International journal of forecasting, 2021, 37(4): 1748-1764.
PDF(1217 KB)
