A hybrid forecasting model for very short-term wind speed prediction based on secondary decomposition and deep learning algorithms.

Wind power generation helps to save energy and reduce emissions. Accurate wind speed prediction can ensure the safe integration of wind power into the energy grid, but due to the intermittent and volatile nature of wind, it brings great difficulties to wind speed prediction. To solve this issue, this paper develops a hybrid forecasting model called WT-VMD-LSTM-TCN, where the wavelet transform (WT) is used to decompose the original wind speed into multiple detailed components and an approximate component, then the variational mode decomposition (VMD) is employed to further decompose the first detailed component, and several intrinsic mode functions and a residual term are obtained. Subsequently, the LSTM-TCN model is established on each component obtained by WT and VMD, where the component is first input into the long short-term memory (LSTM), and then the output sequence of LSTM is input into the temporal convolutional network (TCN) for processing. Ultimately, the predicted results of all components from WT-VMD are reconstructed to obtain the predicted value of wind speed. The performance of the model is verified by simulation experiments with three datasets. The experimental results show that: (a) The developed LSTM-TCN model integrates the feature extraction methods of LSTM and TCN, and the feature extraction ability is more comprehensive, which can improve the forecasting performance of a single model; (b) VMD is used to decompose the subsequence with the largest error, which reduces the difficulty of the prediction of this subsequence; (c) WT-VMD-LSTM-TCN is superior to other comparison models in three datasets, which verifies that the model has good applicability. [ABSTRACT FROM AUTHOR]