Tan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tan Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Guiping Liu
Inner Mongolia University of Technology
3 shared publications - Kunjie Liu
New Energy Branch of Huadian Energy Co
3 shared publications - Na Liu
Inner Mongolia University of Technology
3 shared publications - Jiajia Ma
Inner Mongolia University of Technology
2 shared publications - Zhonghao Zhang
Inner Mongolia University of Technology
2 shared publications - Long Yang
Inner Mongolia University of Technology
1 shared publication
Latest Publications
- 3 August 2026
- Published by Springer Nature
- p. 642-656
YOLO-SACAM: A Switchable Convolution and Attention-Based YOLO Network for Wind Turbine Blade Defects Detection
- 3 August 2026
- Published by Springer Nature
- p. 642-656
YOLO-SACAM: A Switchable Convolution and Attention-Based YOLO Network for Wind Turbine Blade Defects Detection
- Open Access
- 21 July 2026
- Published by Elsevier in Applied Energy
- Vol. 424
DS-MS-convformer: Ultra-short-term wind power prediction based on dual-stream multi-scale convolutional transformer and hierarchical dynamic fusion
- 21 July 2026
- Published by Elsevier in Applied Energy
- Vol. 424
Open AccessDS-MS-convformer: Ultra-short-term wind power prediction based on dual-stream multi-scale convolutional transformer and hierarchical dynamic fusion
- Open Access
- 3 February 2026
- Published by Elsevier in SSRN Electronic Journal
DS-MS-Convformer: Ultra-Short-Term Wind Power Prediction Based on Dual-Stream Multi-Scale Convolutional Transformer and Hierarchical Dynamic Fusion
Against the backdrop of global energy transition and large-scale grid integration of wind power, ultra-short-term wind power prediction is crucial for ensuring power grid security and the efficient operation of wind farms. However, the inherent nonstationarity of wind power sequences stems from the complex coupling of time-domain transient disturbances and frequency-domain periodic fluctuations, posing two core challenges for high-precision prediction: modelling the time-frequency coupling effect and capturing multi-scale dynamic features. Existing deep learning methods often struggle to characterise this cross-scale dynamic interaction mechanism simultaneously and effectively. To address this, this study proposes a wind power prediction method based on Dual-Stream(DS) time-frequency feature decoupling modelling and hierarchical dynamic fusion. First, the technique explicitly decouples and collaboratively learns time-domain dynamic and frequency-domain periodic features through a dual-stream architecture. Furthermore, it introduces a Multi-Scale Convolutional-enhanced Transformer(MS-Convformer) that integrates local convolution and global self-attention to capture second- to minute-level turbulent fluctuations and long-period trends. Finally, through a hierarchical dynamic fusion strategy guided by a gating mechanism and cross-attention, it achieves adaptive weighting and structured integration of multi-scale features. Experimental results on real wind farm datasets show that, compared with mainstream deep learning methods, the DS-MS-Convformer method proposed in this paper achieves significantly higher prediction accuracy, providing adequate technical support for grid integration and renewable energy consumption.
- 3 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDS-MS-Convformer: Ultra-Short-Term Wind Power Prediction Based on Dual-Stream Multi-Scale Convolutional Transformer and Hierarchical Dynamic Fusion
Against the backdrop of global energy transition and large-scale grid integration of wind power, ultra-short-term wind power prediction is crucial for ensuring power grid security and the efficient operation of wind farms. However, the inherent nonstationarity of wind power sequences stems from the complex coupling of time-domain transient disturbances and frequency-domain periodic fluctuations, posing two core challenges for high-precision prediction: modelling the time-frequency coupling effect and capturing multi-scale dynamic features. Existing deep learning methods often struggle to characterise this cross-scale dynamic interaction mechanism simultaneously and effectively. To address this, this study proposes a wind power prediction method based on Dual-Stream(DS) time-frequency feature decoupling modelling and hierarchical dynamic fusion. First, the technique explicitly decouples and collaboratively learns time-domain dynamic and frequency-domain periodic features through a dual-stream architecture. Furthermore, it introduces a Multi-Scale Convolutional-enhanced Transformer(MS-Convformer) that integrates local convolution and global self-attention to capture second- to minute-level turbulent fluctuations and long-period trends. Finally, through a hierarchical dynamic fusion strategy guided by a gating mechanism and cross-attention, it achieves adaptive weighting and structured integration of multi-scale features. Experimental results on real wind farm datasets show that, compared with mainstream deep learning methods, the DS-MS-Convformer method proposed in this paper achieves significantly higher prediction accuracy, providing adequate technical support for grid integration and renewable energy consumption.