Search

Wind energy is an important green energy. The use of wind energy can alleviate the pressure caused by the shortage of traditional energy. The wind speed is affected by many factors, which makes it difficult to forecast accurately. Most wind speed forecasting methods only consider the wind speed data. The other influence factors are usually ignored. In this paper, we use traditional wind speed data and weather factors as the input of our proposed model. In the proposed model, wavelet threshold is employed to reduce the noise of raw wind speed data. We apply grey relational analysis to select the weather factors that have great influence on wind speed. The wind speed data are the input vectors of Elman neural network (Elman) and back propagation optimized by cuckoo search. Weather factors are the input vectors of WNN-GRNN which combines the wavelet neural network (WNN) and general regression neural network (GRNN). Finally, the forecasting results of the weather factors and wind speed data are combined by variance reciprocal method. The data sets at Kalaeloa Oahu, Hawaii are chosen to test the validity of the proposed model. The results show that the proposed model has obvious advantages compared to other benchmark forecasting models. [ABSTRACT FROM AUTHOR]

As one of the effective renewable energy sources, wind energy has received attention because it is sustainable energy. Accurate wind speed forecasting can pave the way to the goal of sustainable development. However, current methods ignore the temporal characteristics of wind speed, which leads to inaccurate forecasting results. In this paper, we propose a novel SSA-CCN-ATT model to forecast the wind speed. Specifically, singular spectrum analysis (SSA) is first applied to decompose the original wind speed into several sub-signals. Secondly, we build a new deep learning CNN-ATT model that combines causal convolutional network (CNN) and attention mechanism (ATT). The causal convolutional network is used to extract the information in the wind speed time series. After that, the attention mechanism is employed to focus on the important information. Finally, a fully connected neural network layer is employed to get wind speed forecasting results. Three experiments on four datasets show that the proposed model performs better than other comparative models. Compared with different comparative models, the maximum improvement percentages of MAPE reaches up to 26.279%, and the minimum is 5.7210%. Moreover, a wind energy conversion curve was established by simulating historical wind speed data. [ABSTRACT FROM AUTHOR]

With the growth of global energy demand, the proportion of the total installed wind capacity continues to increase. Wind speed forecasting is essential to enhance the utilization of wind energy. However, it is not easy to make accurate wind speed forecasting since wind speed time series data has nonlinearity, fluctuation, and intermittence. These features of wind speed time series data make classical models unable to obtain expected forecasting results. Many researchers proposed wind speed forecasting models to overcome the shortage. Nevertheless, some wind speed prediction methods are limited because they cannot mine all implicit features of wind speed data. This paper proposes a novel wind speed forecasting model that can capture all implicit information of wind speed data and obtain accuracy prediction results. To be specific, ensemble empirical mode decomposition (EEMD) is firstly applied to remove the noise in the original wind speed data. Secondly, we build a novel deep learning model based on the attention mechanism and convolutional neural network (CNN). The proposed forecasting model can focus the important part of wind speed data and reduce the high computational complexity of CNN. Finally, a full connect neural network layer is employed to obtain wind speed forecasting results. In order to validate the performance of the proposed model, we take the wind speed data of the M2 tower at 20-meter height of the National Wind Power Technology Center of the United States as an example. The experimental results demonstrate that the forecasting errors of the proposed model are smaller than other comparative models. And the Diebold-Mariano test confirms that the proposed model exhibits a significant difference in performance compared with the comparison models. [ABSTRACT FROM AUTHOR]

Highlights • This paper proposed a novel combined model based on echo state network. • A new dataset division mechanism is applied in this paper. • ESN is initially applied to combine the intermediate forecasting results of four hybrid models. • The proposed model is tested comprehensively in different wind speed sites. Abstract Accurate wind speed forecasting plays a crucial role in wind power plants and wind systems. Numerous studies that dedicated to enhance wind speed forecasting accuracy have been proposed. Nevertheless, some classical models are not good at dealing with nonlinear time sequence, and artificial intelligence are easy fall into local optimum. Based on this, this paper proposed a novel combined model for wind speed forecasting, which combined hybrid models based on decomposition method and optimization algorithm. In this approach, four distinct hybrid models are proposed and to additionally enhance the forecasting performance, ESN (Echo state network) is initially applied to integrate all the results obtained by each hybrid model and achieve the ultimate forecasting results. Besides, a distinct data set division mechanism is adopted in the multi-step wind speed forecasting. To verify the effectiveness and versatility of the proposed combined model, the wind speed data of 20 m, 50 m, 80 m per minute of the M2 tower from the National Wind Power Technology Center, United States, are utilized as case studies. The experimental results indicate that the proposed combined model performs better than other conventional methods. [ABSTRACT FROM AUTHOR]