Short-term wind speed prediction based on feature extraction with Multi-task Lasso and Multilayer Perceptron

In short-term wind speed prediction, different features in the time window have different degrees of influence on the prediction results. However, the importance of different features in the time window is mostly treated equally, which results in the deficiency of responding promptly to the time-varying characteristics of wind speed and treating differently the time window feature weights that affect the prediction accuracy. Hence, a novel model called WTCGRU is proposed to improve the prediction accuracy by fully considering the influence of different features in the time window during wind speed prediction. In WTCGRU, the weights of different features in the time window are sampled through an adaptive genetic approach, which is called importance sampling, and fed into a hybrid model composed of GRU and TCN, to predict more precisely the short-term wind speed; This step is executed repeatedly until WTCGRU's prediction accuracy is higher than a predefined threshold. Finally, theoretical experiments are carried out on the wind speed dataset from Szeged of Hungary, and it is shown that the WTCGRU has outperformed the mainstream short-term wind speed prediction model TCN, BILSTM, CNN-LSTM, and ensemble-CNN.

Wind energy is known for its uncertainty and volatility, necessitating accurate wind speed prediction for stable wind farm operations. To enhance wind speed prediction accuracy, this study proposes a BP neural network (BPNN) short-term wind speed prediction model based on the Improved Dung Beetle Optimization (IDBO) algorithm. Addressing the issue of local optimization and reduced accuracy in the BPNN optimized by the Dung Beetle Optimization (DBO) algorithm, the circle chaotic mapping is utilized for population initialization to achieve a more uniform initial distribution. The improved sine-cosine algorithm, triangle wandering strategy, and adaptive weight coefficient are then employed to optimize dung beetle positions, balancing global exploration and local development capabilities and improving the algorithm’s search performance. Finally, the improved DBO algorithm optimizes the weights and thresholds of the BPNN, and the IDBO-BPNN prediction model was constructed. Simulation experiments were conducted based on wind speed data from a wind farm in Ohio, USA. The IDBO-BPNN model was compared with other prediction models, and error evaluation indexes were introduced to evaluate the experimental results. The findings demonstrate that the suggested model yields the most accurate predictions and achieves the optimal error evaluation indexes. MAE, MSE, RMSE, NSE and R2 of dataset 1 are 0.42247, 0.28775, 0.53642, 88.8785%, 89.161%, those of dataset 2 are 0.28283, 0.14952, 0.38668, 85.7383%, 86.577%, and those of dataset 3 are 0.45406, 0.39268, 0.62664, 84.3859%, 84.931%. In particular, compared with BPNN model, the five evaluation indexes of the IDBO-BPNN model promoted by 41.53%, 57.38%, 34.71%, 24.91%, and 11.44%, respectively in dataset 3. Therefore, that the proposed IDBO-BPNN model exhibits higher accuracy in short-term wind speed prediction, indicating its feasibility and superiority in the realm of wind energy.

This paper proposes a new combined prediction model for short-term wind speed prediction. The article uses Numerical Weather Prediction (NWP) and actual wind speed as input to the CNN_GRU model. The normalization method is used to solve the problem of the difference in magnitude between different data types. In order to extract the data characteristics between wind direction, temperature, air pressure, numerical weather forecast wind speed and actual wind speed, a continuous data matrix is constructed. The processed data set is divided into training set and test set. First, the characteristics of the data set are extracted using a Convolutional Neural Network (CNN). The fully connected layer then processes the extracted features and inputs them to the GRU network. Finally, the final predicted wind speed is obtained through the output layer. In order to avoid the gradient dispersion caused by the Sigmoid, this paper uses the Relu as the activation function of the network. The CNN_GRU model is compared with the CNN model and the continuous method under the same conditions. The results show that the proposed CNN_GRU model has the best effect in short-term wind speed prediction.

Predicting short wind speed with a hybrid model based on a piecewise error correction method and Elman neural network

A new two-stage decomposition and integrated hybrid model for short-term wind speed prediction

Wind energy is highly valued by the power industry for its cleanliness and sustainability. Precise wind speed forecast is a vital condition for electricity system to give play to its high efficiency stably. However, traditional prediction models fail to effectively decompose and refine key information in data, resulting in insufficient stability and accuracy of prediction. To enhance the model’s generalization capability and fully utilize the advantages of diverse models, this paper establishes a combined model which includes data fuzzy strategy and combination strategy. In this model, the triangular membership function divides the data into different fuzzy granularity, focusing on the key features of the data, and multi-objective salp swarm algorithm (MOssa) generates a Pareto optimal solution set as weights to combine the sub-models, so as to achieve accurate predictions. Based on point prediction, interval prediction further realizes uncertainty analysis of different probabilities and provides more comprehensive data analysis information by calculating interval range through prediction error distribution function and confidence level. Chinese real wind speed data were used to assess how well the model performs. The findings reveal that the constructed information strategy and combination strategy notably enhance prediction robustness and accuracy.

It is well known that the inherent instability of wind speed may jeopardize the safety and operation of wind power generation, consequently affecting the power dispatch efficiency in power systems. Therefore, accurate short-term wind speed prediction can provide valuable information to solve the wind power grid connection problem. For this reason, the optimization of feedforward (FF) neural networks using an improved flower pollination algorithm is proposed. First of all, the empirical mode decomposition method is devoted to decompose the wind speed sequence into components of different frequencies for decreasing the volatility of the wind speed sequence. Secondly, a back propagation neural network is integrated with the improved flower pollination algorithm to predict the changing trend of each decomposed component. Finally, the predicted values of each component can get into an overlay combination process and achieve the purpose of accurate prediction of wind speed. Compared with major existing neural network models, the performance tests confirm that the average absolute error using the proposed algorithm can be reduced up to 3.67%.

With the development of the wind power, the prediction of wind speed has received much attention. In this paper, the support vector regression based local predictor (SVRLP) is combined with mathematical morphology, named as SVRLP-MM, and applied to the short-term wind speed prediction. Through the mathematical morphology, the wind speed time series would be decomposed into two subsequences, named "baseline" and "noise", with different frequencies and wave characteristics. Then the SVRLP is applied to predict each subsequences separately, the final wind speed prediction result is equal to the sum of each subsequences' prediction result. The proposed SVRLP-MM is evaluated with the real world wind speed data, and is compared with the support vector regression (SVR), the support vector regression based local predictor (SVRLP) and the autoregressive moving average (ARMA). The results demonstrate that the proposed method can achieve a better performance than the other methods.

Research on short-term wind speed prediction based on deep learning model in multi-fan scenario of distributed generation

The precise forecasting of wind speeds is critical to lessen the harmful impacts of wind fluctuations on power networks and aid in merging wind energy into the grid system. However, prior research has predominantly focused on point forecasts, often overlooking the uncertainties inherent in the prediction accuracy. For this research, we suggest a new approach for forecasting wind speed intervals (PI). Specifically, the actual wind speed series are initially procured, and the complete ensemble empirical mode decomposition coupled with adaptive noise (CEEMDAN) method decomposes the actual wind speed series into constituent numerous mode functions. Furthermore, a generative adversarial network (GAN) is utilized to achieve the wind speed PI in conjunction with the multivariate linear regression method. To confirm the effectiveness of the suggested model, four datasets are selected. The validation results suggest that this suggested model attains a superior PI accuracy compared with those of numerous benchmark techniques. In the context of PI of dataset 4, the PINAW values show improvements of 68.06% and 32.35% over the CEEMDAN-CNN and VMD-GRU values in single-step forecasting, respectively. In conclusion, the proposed model excels over the counterpart models by exhibiting diminished a PINAW and CWC, while maintaining a similar PICP.

The wind is a highly complex phenomenon that depends on geographical and environmental conditions. Wind speed depends on many variables such as temperature, pressure, humidity, and other lower atmospheric conditions, and thus mathematical modeling is highly complex and requires high computational power and time for wind speed prediction. Over the years, data-driven models for multi-step ahead time-series predictions have been gaining attention and are still in the evolutionary stage. Improvements in prediction models help the wind generation systems to operate efficiently. The accumulation of errors in the multi-step prediction creates a challenge in formulating novel prediction models. A prediction model based on long short-term memory (LSTM) is proposed in this study for short-term wind prediction up to a prediction horizon of 3 hours ahead. Hyperparameters of the LSTM model are tuned by Bayesian optimization. The wind speed data of two different sites are considered for the evaluation of the proposed model. Further, Support vector Regression based on the Multiple Input Multiple Output (MIMO) strategy is used to compare the performance of the proposed model. Bayesian optimized Long Short Term Memory (BO-LSTM) model shows nearly 30% and 16 % improvement in the MSE and RMSE scores, respectively, over the SVR model.

Wind speed prediction in short term is required to asses the effect of wind on different objects in action in free space, like rockets, navigating ships and planes, guided missiles satellites in launch etc. Forecasting also helps in usage of wind energy as an alternative source of energy in Electrical power generation plants. The wind speed depends on the values of other atmospheric variables, such as pressure, moisture content, humidity, rainfall etc. This paper reports a Support Vector Machine model for short term wind speed prediction. The model uses the values of these parameters, obtained from a nearest weather station, as input data. The trained model is validated using a part of data. The model is then used to predict the wind speed, using the same meteorological information.

At present, most of the short-term wind speed forecasting researches directly use the original data as the input or break them down, and take the decomposed series as the input for forecasting model. There is a lack of feature analysis of the original data and the decomposed series. In this paper, from the perspective of feature analysis of wind speed, Ensemble Empirical Mode Decomposition (EEMD) and Convolutional Neural Networks (CNN) are used to decompose the sequence and extract features, and Multilayer Perceptron (MLP) is used to predict the wind speed. Firstly, EEMD is used to decompose the wind speed into a series of subsequences; Secondly, CNN is used to extract the features of each decomposition layer, and the input variables of each decomposition layer are constructed; Finally, MLP is used to predict each decomposition layer; At the same time, Adam is used to optimize the parameters of CNN and MLP. The results of case study and comparison show that EEMD-CNN-MLP-Adam has high prediction and good generalization, which can provide reference for wind speed prediction in different regions and periods.

Under the global trend of renewable energy development, various advanced techniques such as forecasting algorithm, intelligent computation, and optimal control are expected to make the complex and uncertain renewable energy system stable and profitable in the near future. This paper presents a new control strategy for large-scale wind energy conversion systems to achieve a balance between power output maximization and operating cost minimization. First, an intelligent maximum power point tracking (IMPPT) algorithm is proposed such that short-term wind speed prediction, wind turbine dynamics, and MPPT are collectively considered to improve system efficiency. Second, in view of a spatial and temporal distribution of wind speed disturbances, a box uncertainty set is embedded in the forecast wind speed, which is likely more realistic for practicing engineers. Then, the IMPPT and box uncertainties are applied to the wind energy conversion system (WECS) control strategy, which is formulated as a min-max optimization problem and efficiently solved with semi-definite programming (SDP). Finally, a comparison with the conventional MPPT control method demonstrates that the proposed approach can obtain higher efficiency, which validates this paper.

Wind energy is one of the promising renewable energy sources that are ideal for daily use, especially in the area with sufficient wind blows like Indonesia. Wind speed caused by wind energy is a driving force for wind turbines to produce electrical power. One problem in wind turbine management is to predict the speed of the wind in the short term for efficiency. In this research, forecasting of short-term wind speed was done in the city of Sibolga by uses an Elman recurrent neural network based on meteorological data: temperature, humidity, and air pressure to predict over the next ten days. Four prediction models were developed for this purpose based on training parameters and dataset used. The wind speed forecasting produces MAPE error values of 20.02% in the first model, 23.31% in the second model, 18.15% in the third model, and 12.51% in the fourth model. The fourth model was capable of predicting with the lowest error and, therefore, considered to be useful for wind turbine management.