M2STAN: Multi-modal multi-task spatiotemporal attention network for multi-location ultra-short-term wind power multi-step predictions

•Multi-modal Multi-task Spatiotemporal Attention Network (M2STAN) model for wind power prediction.•Implementation of M2STAN on 23 wind farms in China for ultra-short-term power prediction.•Accuracy and computational efficiency were used to evaluate the performance of M2STAN.•Comparisons with reporte...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Applied energy Ročník 324; s. 119672
Hlavní autoři:	Wang, Lei, He, Yigang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 15.10.2022
Témata:	artificial intelligence energy Graph attention network M2STAN Multi-modal learning Multi-task learning power generation prediction regression analysis wind wind farms wind power Wind power prediction MTL GLSTM GRU GPU WD M2GSNet Multi-task learning SVR RNN GCDLA WPP Bi-GRU WP WS MI EMD M2STAN LSTM Seq2seq AD NWP S-GAT RMSE AP MAE GCN Wind power prediction RF GAT Multi-modal learning TP Graph attention network
ISSN:	0306-2619, 1872-9118
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•Multi-modal Multi-task Spatiotemporal Attention Network (M2STAN) model for wind power prediction.•Implementation of M2STAN on 23 wind farms in China for ultra-short-term power prediction.•Accuracy and computational efficiency were used to evaluate the performance of M2STAN.•Comparisons with reported models and ablation strategies support the design of individual modules in M2STAN.•M2STAN considering spatiotemporal correlations proves potential for large-scale wind farm applications. In recent years, wind power has continued to emerge as a key source of renewable energy. When large-scale wind farm clusters are connected to the grid for power generation, accurate multi-location ultra-short-term wind power predictions carry significant value in terms of ensuring the safety, stability, and economical operation of the power system. However, there are complex temporal and spatial correlations among multiple wind farms in multiple locations, which makes wind power predictions involving wind farm clusters very challenging. The development of artificial intelligence technology, especially graph machine learning, provides new approaches for modeling such spatiotemporal correlations. In addition, compared with single-step forecasting, multi-step forecasting can better reflect the general situation, and thus, it is more widely applicable in reality. To optimize multi-step wind power predictions in multiple locations, this report proposes a Multi-Modal Multi-Task Spatiotemporal Attention Network (M2STAN) model. The developed model employs a graph attention network and a bidirectional gated recurrent unit (Bi-GRU) to model the spatial and temporal dependence, respectively. In addition, the introduction of multi-modal and multi-task learning strategies improves the accuracy and computational efficiency of this predictive model. The results indicate that the proposed method is superior to existing methods, including support vector regression, Bi-GRU, multi-modal multi-task graph spatiotemporal networks, and graph convolutional deep learning architectures in terms of prediction performance.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0306-2619 1872-9118
DOI:	10.1016/j.apenergy.2022.119672