Wind power plays a crucial role in the secure conversion and management of the power system. Therefore, this study proposes a hybrid model for short-term wind power forecasting, which consists of the variational mode decomposition(VMD), the K-means clustering algorithm and long short term memory(LSTM) network.The combination model is conducted as follows: the VMD decomposes the raw wind power series into a certain number of sub-layers with different frequencies; K-means as a data mining approach is executed for splitting the data into an ensemble of components with similar fluctuant level of each sub-layer; LSTM is adopted as the principal forecasting engine for capturing the unsteady characteristics of each component. Eventually, the forecasting results would be generated by aggregating the predicted components.To evaluate the fitting capacity of the proposed model, seven different models including the back propagation neural network(BP) approach, the Elman neural network(ELMAN), the LSTM approach, the VMD-BP approach, the VMD-Elman approach, the VMD-LSTM approach and the VMD-Kmeans-LSTM approach are implemented on four wind power series for multiple scales. The experimental results demonstrate the best performance in favour of the proposed model.

The larger capacity of power converters increases with the size of wind turbines over the years, which implies more failures occur in the components of power converter. Meanwhile, the strategies of fault diagnosis of power converter in wind turbine are still under discussion and research. The main purpose of this paper is proposing a strategy containing wavelet transform, feature analysis, judgment and back propagation neural network (BPNN) classification (WT-FA-JD-BP) to identify the single and double power components open-circuit faults accurately, happen in grid-side converter (GSC) of permanent magnet synchronous generator (PMSG) wind turbine systems. First, as the original signals, the three-phase bridge legs voltage of the GSC are collected under different faults. Second, wavelet transform is used to decompose and reconstruct the signals. Third, a new method includes feature analysis and judgment is conducted to amplify the divergence of data obtained by wavelet transform. Finally, the data are used as the inputs of BPNN for decision-making and classification. The simulation and experimental results show that the proposed strategy can classify the single and double open-circuit faults, and the accuracy is higher than that without data feature analysis and judgment.

A variety of supervised learning methods using numerical weather prediction (NWP) data have been exploited for short-term wind power forecasting (WPF). However, the NWP data may not be available enough due to its uncertainties on initial atmospheric conditions. Thus, this study proposes a novel hybrid intelligent method to improve existing forecasting models such as random forest (RF) and artificial neural networks, for higher accuracy. First, the proposed method develops the predictive deep belief network (DBN) to perform short-term wind speed prediction (WSP). Then, the WSP data are transformed into supplementary input features in the prediction process of WPF. Second, owing to its ensemble learning and parallelization, the random forest is used as supervised forecasting model. In addition, a data driven dimension reduction procedure and a weighted voting method are utilized to optimize the random forest algorithm in the training process and the prediction process, respectively. The increasing number of training samples would cause the overfitting problem. Therefore, the k-fold cross validation (CV) technique is adopted to address this issue. Numerical experiments are performed at 15-min, 30-min, 45-min, and 24-h to indicate the superiority and signal advantages compared with existing methods in terms of forecasting accuracy and scalability.

Wind energy plays an increasingly important role in economic development. In this study, we propose a hybrid short-term wind-speed forecasting model comprising multiscale mathematical morphological decomposition (MMMD), K-means clustering algorithm, and stacked denoising autoencoder (SDAE) networks. First, in contrast to traditional signal-decomposing tools, the original wind-speed sequence is decomposed into a series of subsequences with different frequencies and fluctuant levels using the adaptive multiscale mathematical morphological algorithm directly in the time domain. The signal does not need to be transferred from the time domain to the frequency domain; hence, the accuracy can be considerably improved. Moreover, this is the first study that uses a time domain signal-decomposing tool in a hybrid wind forecasting model. Next, the data are split into different clusters of similar frequencies and fluctuant level subsequences using the K-means algorithm. The characteristics of each cluster are then captured using the SDAE as the core forecasting unit. Finally, the predictions of all subsequences are aggregated to obtain the final wind speed. The data from two real wind turbines are used to evaluate the performance of the proposed model, and the forecasting results are compared with five different benchmark models, namely, backpropagation neural network (BPNN), stacked denoising autoencoder (SDAE), mathematical morphology–backpropagation, mathematical morphology–SDAE, and K-means–SDAE for multiple scales, and two novel hybrid wind forecasting models namely, wavelet transform (WT)-K-means-SDAE and variation mode decomposition (VMD)-K-means-long short-term memory networks (LSTMs). The results of the comparison demonstrate that the proposed model provides a short-term wind-speed forecasting method whose prediction accuracy decreases with time; however, the proposed model achieves a better performance in comparison with other exiting models. At same time, the proposed model significantly increases the prediction accuracy of wind-speed forecasting and can be a reference for future research in this area.