Search

Accurate wind power forecasting is of great significance for power system operation. In this study, a triple-stage multi-step wind power forecasting approach is proposed by applying attention-based deep residual gated recurrent unit (GRU) network combined with ensemble empirical mode decomposition (EEMD) and crisscross optimization algorithm (CSO). In the data processing stage, the EEMD is used to decompose the wind power/speed time series and a bi-attention mechanism (BA) is applied to enhance the sensitivity of model to the important information from both time and feature dimension. In the prediction stage, a series-connected deep learning model called RGRU consisting of the residual network and GRU is proposed as the forecasting model, aiming to make full use of extracting the static and dynamic coupling relationship among the input features. In the retraining-stage, a high-performance CSO algorithm is adopted to further optimize the fully-connected layer of RGRU model so as to improve the generalization ability of the model. The proposed method is validated on a wind farm located in Spain and the experimental results demonstrate that the proposed hybrid model has significant advantage over other state-of-the-art models involved in this study in terms of prediction accuracy and stability.

Accurate forecasts of wind power generation are essential for the operation of wind farms. But for the newly developed stations, it is difficult to make accurate prediction because there are no sufficient historical data available. It will thus be interesting to explore new data augmentation and prediction modeling approach adaptive to such new-built wind farms. In this regard, a novel asexual-reproduction evolutionary neural network (ARENN) for short-term wind power prediction based on Wasserstein generative adversarial network with gradient penalty (WGANGP) and ensemble empirical mode decomposition (EEMD) is presented in this paper. To solve the dilemma that new-built wind farms lack sufficient wind power data, the WGANGP is first applied to generate realistic data with a similar distribution of real data to augment the training dataset, which is further decomposed into a series of more stable subsequences by the EEMD so as to reduce the prediction difficulty of the machine learning model. In this study, a novel ARENN prediction model is developed to make the short-term wind power prediction, in which an asexual-reproduction evolutionary approach is first proposed to optimize the neural network based on a set of different loss functions that facilitate the population of network parameters approximating to the global optimum along different error surfaces in the evolutionary process. The proposed approach is validated on the data collected from the wind farm located in Spain and the predicted results demonstrate the advantage of our proposed approach over other methods involved in this study.

Although machine learning methods have been widely applied in the wind power prediction field, they are not suitable for building the prediction model of a new-built wind farm because of no sufficient historical data. In this study, a novel deep transfer learning approach is proposed for addressing the few-shot learning problem in multi-step ahead wind power prediction. In the pre-training stage, several convolutional neural networks (CNNs) in parallel are separately connected to the long short-term memory network (LSTM), thus forming a unique serio-parallel CNNs-LSTM (CL) feature extractor. The CL utilizes the CNNs and LSTM to extract both the meteorological and temporal feature information of the neighboring wind farms for facilitating the prediction modeling of the source wind farm. In the transfer-training stage, a transfer strategy is designed to transfer partial network parameters of a well-trained CL feature extractor to construct the prediction model of the target wind farm. In addition, a personalized-training strategy is implemented by using crisscross optimization (CSO) to retrain the parameters of fully-connected layer. The proposed method is validated on a swarm of wind farms located in China and the experimental results show its obvious superiority over the non-transfer models involved in this study.

A wireless power transmission (WPT) requires high switching frequency to achieve energy transmission, however, existing switching devices cannot satisfy the requirements of high-frequency switching, and the efficiency of current WPT is too low. Compared with the traditional power inductors and capacitors, fractional-order elements (FOEs) in WPT can realize necessary functions though requiring a lower switching frequency, which leads to a more favorable high-frequency switching performance with a higher efficiency. In this study, a generalized fractional-order WPT (FO-WPT) is established, followed by a comprehensive analysis on its WPT performance and power efficiency. Through extensive simulations of typical FO wireless power domino-resonators (FO-WPDRS), the functionality of the proposed FO-WPT for medium and long-range WPT is demonstrated. The numerical results show that the proposed FOE-based WPT solution has a higher power efficiency and lower switching frequency than conventional methods.

Wind power forecasting is crucial for the economic dispatch and operation of power system. In this study, a novel hybrid wind power prediction approach is proposed by applying a cascaded deep learning model to extract the implicit meteorological and temporal characteristics of each subseries generated by a two-layer of mode decomposition method. In the proposed model, the empirical mode decomposition is employed to decompose the original time series into a set of intrinsic mode functions (IMFs) and the variational mode decomposition is applied to further decompose the IMF1 sub-layers into several sub-series because of the irregular feature of IMF1. To make use of the coupling relationship between wind power sub-layer, wind speed sub-layer and wind direction, convolutional neural network is used to extract the implicit features of these relationship and then long short-term memory utilizes these features as inputs and further extract the temporal correlation hidden features in each time sub-series. The eventual predicted results are obtained by superimposing the predicted values of all subsequences. The experimental results illustrate that: (a) The prediction performance is obviously improved when the proposed two-layer of decomposition is considered. (b) To achieve better prediction accuracy, it is proven to be an effective way to apply convolutional neural network and long short-term memory to extract the implicit meteorological relationship and the temporal correlation characteristic hidden in each decomposed time sub-series, respectively. (c) The proposed hybrid model outperforms other hybrid models involved in this study and shows a promising prospect in the short-term wind power prediction.