| 引用本文: | 樊雅洁,王聪,张宏立,马萍,李新凯.组合聚类和深度学习模型的风电场群风速预测[J].哈尔滨工业大学学报,2024,56(12):71.DOI:10.11918/202311053 |
| FAN Yajie,WANG Cong,ZHANG Hongli,MA Ping,LI Xinkai.Wind speed prediction of wind farm group by combining clustering and deep learning model[J].Journal of Harbin Institute of Technology,2024,56(12):71.DOI:10.11918/202311053 |
|
| 摘要: |
| 为提高规模化风电场群的风速预测精度,进而保障中国电网的安全稳定运行,提出了一种基于粒子群投影寻踪聚类算法结合NS-L-Transformer的风电场群短期风速混合预测模型。首先,通过变分模态分解、去伪分量和小波变换的方法对采集的风速数据集进行处理,得到滤除噪声干扰后的风速数据集。其次,考虑风电场群间的风速空间关联特性,根据其风速波动特征,采用粒子群投影寻踪聚类算法分析了风电场群间的空间相关性,根据算法所得到的评价指标对风电场群进行了场群关联性最优分类,并构造了分类后的高维风速数据集。最后,通过Transformer模型的自注意力机制结合LSTM模型的门控单元机制捕捉风速时间序列的局部特征,提出了NS-L-Transformer模型对所构造的具有局部特性的高维风速数据集进行了风速预测。选用中国东南某地区风电场群的风速数据进行了仿真分析,研究结果表明,采用分类后的高维数据集进行风速预测较单一风速数据集的预测精度有较大的提升；相较于Transformer模型,NS-L-Transformer的预测误差减少,从而验证了本研究所提混合预测模型的有效性。 |
| 关键词: 风速预测 风速数据降噪 风电场群分类 粒子群投影寻踪聚类算法 NS-L-Transformer模型 |
| DOI：10.11918/202311053 |
| 分类号:TM614; TP183 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(52267010)；国家重点研发计划项目(2021YFB1507000)；新疆维吾尔自治区自然科学基金 (2022D01E3,2D01C367) |
|
| Wind speed prediction of wind farm group by combining clustering and deep learning model |
|
FAN Yajie1,WANG Cong1,ZHANG Hongli2,MA Ping1,LI Xinkai1
|
|
(1.School of Electrical Engineering, Xinjiang University, Urumqi 830017, China; 2.School of Intelligence Science and Technology (School of Future Technology), Xinjiang University, Urumqi 830017, China)
|
| Abstract: |
| To improve the wind speed prediction accuracy of large-scale wind farm clusters and ensure the safe and stable operation of China’s power grid, a short-term wind speed hybrid prediction model for wind farm groups based on particle swarm optimization combined with projection pursuit clustering and NS-L-Transformer was proposed. Firstly, the collected wind speed dataset was processed by the methods of variational mode decomposition, depseudo-component removal and wavelet transform, and the wind speed dataset after filtering out noise interference was obtained. Secondly, considering the spatial correlation characteristics of wind speed among wind farm groups, according to the wind speed fluctuation characteristics, the particle swarm optimization based on projection pursuit clustering algorithm was used to analyze the spatial correlation between wind farm groups. Using the evaluation metrics obtained from the algorithm, an optimal classification of field group correlation was carried out based on their spatial correlations, and the classified high-dimensional wind speed dataset was constructed. Finally, the self-attention mechanism of the Transformer model combined with the gating unit mechanism of the LSTM model captured the local characteristics of the wind speed time series, and the NS-L-Transformer model was proposed to predict the wind speed of the constructed high-dimensional wind speed dataset with local characteristics. The wind speed data of a wind farm group in southeast China was selected for simulation analysis, and the results show that the prediction accuracy of wind speed prediction using the classified high-dimensional dataset is greatly improved compared with that of the single wind speed dataset. Furthermore, compared with the Transformer model, the NS-L-Transformer model exhibits reduced prediction errors, which validates the effectiveness of the hybrid prediction model proposed in this paper. |
| Key words: wind speed prediction wind speed data denoising classification of wind farm clusters the particle swarm optimization combined with projection pursuit clustering algorithm（PSO-PPC） NS-L-Transformer model |
