Wind power prediction based on periodic characteristic decomposition and multi-layer attention network

作者：Liao, Xuechao; Liu, Zhenxing^*; Zheng, Xiujuan; Ping, Zuowei; He, Xin

来源：NEUROCOMPUTING, 2023, 534: 119-132.

DOI：10.1016/j.neucom.2023.02.061

• Wind power prediction
• Periodic feature extraction
• Seasonal and trend decomposition
• Temporal pattern attention
• Encoder-decoder network

Aiming at the wind power characteristics of temporality, periodicity and complexity, the periodic law of short-term and long-term repetitive patterns is studied, and an integrated dual-channel prediction model is proposed. A practical periodic characteristic extracting strategy is designed to show the hidden peri-odic law of the original signal. Combining the grid search algorithm with the variation trend of ampli-tude/period, the optimal periodic step is determined. Based on the above analysis, the original signal is decomposed into temporal and periodic components. Then the temporal attention network and the encoder-decoder attention network are schemed out to dispose the two components respectively. Finally, the linear regression attention network is adopted to realize data fitting. The integrated forecast-ing framework can deal with the long-term and short-term dependencies of the original data at the same time, and ensure the rapid convergence of training process, thereby improve the prediction accuracy and stability. The multi-dimensional experimental verification is carried out through the comparison of eval-uation indicators, prediction trends, scatter plots and box plots.

• 单位
  华中科技大学