针对在多风电机组风速预测任务中,卷积运算不适用于提取排布不规则的多风电机组空间相关性的问题,提出一种基于时空注意力-Seq2Seq模型的多风电机组多步风速预测算法。首先使用空间注意力机制强化风速序列的空间相关性,并对常规空间注意力机制进行改进;之后使用Seq2Seq模型中的编码器进行编码;最后使用结合时间注意力机制的解码器计算多风电机组的多步预测结果。以河北市某风电场的实际数据为算例进行实验,结果表明相比其他对比算法,所提算法的平均绝对误差下降约4.3%~15.0%,精度有较大提高。
Abstract
Aiming at the problem of convolution operation is not suitable for extracting spatial correlations of multiple wind turbines with irregular layout in wind speed prediction tasks for multiple wind turbines, a multi-step wind speed prediction algorithm of multiple wind turbines based on the spatial-temporal attention-Seq2Seq model is proposed. Firstly, the spatial attention mechanism is used to strengthen the spatial correlation of wind speed sequences, and the conventional spatial attention mechanism is improved. Then, the encoder in the Seq2Seq model is used to encode the data. Finally, the decoder combined with the temporal attention mechanism is used to calculate the multi-step prediction results of multiple wind turbines. A wind speed dataset of a wind farm in Hebei is used as a case, the results show that the average absolute error of the proposed algorithm is reduced by about 4.3%-15.0% compared with other comparison algorithms, and the accuracy is significantly improved.
关键词
风速 /
深度学习 /
风电机组 /
注意力机制 /
Seq2Seq /
时空相关性
Key words
wind speed /
deep learning /
wind turbines /
attention mechanism /
Seq2Seq /
spatial-temporal correlation
{{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] 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.
[3] 姜明洋, 徐丽, 张开军, 等. 基于季节指数调整的循环神经网络风速时间序列预测[J].太阳能学报, 2022, 43(2): 444-450.
JIANG M Y, XU L, ZHANG K J, et al.Recurrent neural network prediction of wind speed time series based on seasonal exponential adjustment[J]. Acta energiae solaris sinica, 2022, 43(2): 444-450.
[4] 王岩, 陈耀然, 韩兆龙, 等. 基于互信息理论与递归神经网络的短期风速预测模型[J]. 上海交通大学学报, 2021, 55(9): 1080-1086.
WANG Y, CHEN Y R, HAN Z L, et al.Short-term wind speed forecasting model based on mutual information and recursive neural network[J]. Journal of Shanghai Jiao Tong University, 2021, 55(9): 1080-1086.
[5] 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.
[6] 陈金富, 朱乔木, 石东源, 等. 利用时空相关性的多位置多步风速预测模型[J]. 中国电机工程学报, 2019, 39(7): 2093-2106.
CHEN J F, ZHU Q M, SHI D Y, et al.A multi-step wind speed prediction model for multiple sites leveraging spatio-temporal correlation[J]. Proceedings of the CSEE,2019, 39(7): 2093-2106.
[7] 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): 534-542.
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): 534-542.
[8] 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, 35(13): 2723-2735.
WANG C, KOU P.Wind speed forecasts of multiple wind turbines in a wind farm based on integration model built by convolutional neural network and simple recurrent unit[J]. Transactions of China Electrotechnical Society, 2020, 35(13): 2723-2735.
[9] ZHU Q M, CHEN J F, SHI D Y, et al.Learning temporal and spatial correlations jointly: a unified framework for wind speed prediction[J]. IEEE transactions on sustainable energy, 2020, 11(1): 509-523.
[10] CHEN G G, TANG B R, ZENG X J, et al.Short-term wind speed forecasting based on long short-term memory and improved BP neural network[J]. International journal of electrical power & energy systems, 2022, 134: 107365.
[11] WANG J Z, SONG Y L, LIU F, et al.Analysis and application of forecasting models in wind power integration: a review of multi-step-ahead wind speed forecasting models[J]. Renewable and sustainable energy reviews, 2016, 60: 960-981.
[12] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]// Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), Doha, Qatar, 2014.
[13] 刘建伟, 刘俊文, 罗雄麟. 深度学习中注意力机制研究进展[J]. 工程科学学报, 2021, 43(11): 1499-1511.
LIU J W, LIU J W, LUO X L.Research progress in attention mechanism in deep learning[J]. Chinese journal of engineering, 2021, 43(11): 1499-1511.
[14] 任欢, 王旭光. 注意力机制综述[J]. 计算机应用, 2021, 41(S1): 1-6.
REN H, WANG X G.Review of attention mechanism[J]. Journal of computer applications, 2021, 41(S1): 1-6.
[15] CORDONNIER J B, LOUKAS A, JAGGI M. On the relationship between self-attention and convolutional layers[EB/OL].2019: arXiv: 1911.03584. https://arxiv.org/abs/1911.03584
[16] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[EB/OL].2020: arXiv: 2010.11929. https://arxiv.org/abs/2010.11929
基金
北京市自然科学基金（4182061）; 中央高校基本科研业务费（2020JG006; 2020MS117）
PDF(1937 KB)
