DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism
With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscal...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/15/4530 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406455205068800 |
|---|---|
| author | Wenhan Song Enguang Zuo Junyu Zhu Chen Chen Cheng Chen Ziwei Yan Xiaoyi Lv |
| author_facet | Wenhan Song Enguang Zuo Junyu Zhu Chen Chen Cheng Chen Ziwei Yan Xiaoyi Lv |
| author_sort | Wenhan Song |
| collection | DOAJ |
| description | With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L<sup>2</sup>)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix. |
| format | Article |
| id | doaj-art-d8b2ffb58b73412aac98155800a87f54 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-d8b2ffb58b73412aac98155800a87f542025-08-20T03:36:22ZengMDPI AGSensors1424-82202025-07-012515453010.3390/s25154530DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention MechanismWenhan Song0Enguang Zuo1Junyu Zhu2Chen Chen3Cheng Chen4Ziwei Yan5Xiaoyi Lv6School of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Intelligence Science and Technology, Xinjiang University, Urumqi 830017, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaWith the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L<sup>2</sup>)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix.https://www.mdpi.com/1424-8220/25/15/4530wind-power forecastingdimensional transformationconvolutional attention mechanismdeep learning |
| spellingShingle | Wenhan Song Enguang Zuo Junyu Zhu Chen Chen Cheng Chen Ziwei Yan Xiaoyi Lv DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism Sensors wind-power forecasting dimensional transformation convolutional attention mechanism deep learning |
| title | DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism |
| title_full | DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism |
| title_fullStr | DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism |
| title_full_unstemmed | DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism |
| title_short | DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism |
| title_sort | dtcmma efficient wind power forecasting based on dimensional transformation combined with multidimensional and multiscale convolutional attention mechanism |
| topic | wind-power forecasting dimensional transformation convolutional attention mechanism deep learning |
| url | https://www.mdpi.com/1424-8220/25/15/4530 |
| work_keys_str_mv | AT wenhansong dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT enguangzuo dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT junyuzhu dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT chenchen dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT chengchen dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT ziweiyan dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism AT xiaoyilv dtcmmaefficientwindpowerforecastingbasedondimensionaltransformationcombinedwithmultidimensionalandmultiscaleconvolutionalattentionmechanism |