Gu Bo

Accurate interval forecasting of wind power is crucial for ensuring the safe, stable, and cost-effective operation of power grids. In this paper, we propose a hybrid deep learning model for day-ahead wind power interval forecasting. The model begins by utilizing a Gaussian mixture model (GMM) to cluster daily data with similar distribution patterns. To optimize input features, a feature selection (FS) method is applied to remove irrelevant data. The empirical wavelet transform (EWT) is then employed to decompose both numerical weather prediction (NWP) and wind power data into frequency components, effectively isolating the high-frequency components that capture the inherent randomness and volatility of the data. A convolutional neural network (CNN) is used to extract spatial correlations and meteorological features, while the bidirectional gated recurrent unit (BiGRU) model captures temporal dependencies within the data sequence. To further enhance forecasting accuracy, a multi-head self-attention mechanism (MHSAM) is incorporated to assign greater weight to the most influential elements. This leads to the development of a day-ahead wind power interval forecasting model based on GMM-FS-EWT-CNN-BiGRU-MHSAM. The proposed model is validated through comparison with a benchmark forecasting model and demonstrates superior performance. Furthermore, a comparison with the interval forecasts generated using the NPKDE method shows that the new model achieves higher accuracy.

For large-scale constructed wind farms, reducing wake loss and improving the overall output power are the main objectives for their optimal operation. Therefore, a wind farm power maximization method based on a multi-strategy improved sparrow search algorithm (MS-ISSA) is proposed in this paper. Integrating the wake propagation mechanism of wind turbines and the characteristics of the classic Jensen wake model, the Jensen–Gaussian wake model and wake superposition model were constructed to accurately calculate the wind farm wake distribution. The constructed Jensen–Gaussian wake model and wake superposition model can accurately describe the non-uniform distribution characteristics of wake velocity. The Sin chaotic model, Cauchy distribution, and hyperparameter adaptive adjustment strategy were used to improve the sparrow search algorithm (SSA), and the optimization ability, convergence speed, and stability of the SSA were improved. Accordingly, considering the maximum output power of the wind farm as the optimization target and axial induction factor as the optimization variable, a coordinated optimization model for wind turbines based on MS-ISSA was proposed to realize the coordinated optimal operation of wind turbines with reduced wake loss. Considering the Danish Horns Rev wind farm as the research object, the results of optimization using particle swarm optimization algorithm, whale optimization algorithm, basic sparrow search algorithm, and MS-ISSA were calculated and analyzed. The calculation results revealed that under different incoming wind conditions, the MS-ISSA exhibited better optimization results than the other optimization algorithms.

Accurate forecasting is the key factor in promoting wind power consumption and improving the stable operation of power systems. A short-term wind power forecasting (WPF) and uncertainty analysis method based on whale optimization algorithm (WOA), least squares support vector machine (LSSVM), and nonparametric kernel density estimation (NPKDE) was proposed in this paper. The advantages of WOA (fast convergence speed and high convergence accuracy) were used to optimize the penalty factor and kernel function width of the LSSVM model, and the calculation speed and forecasting accuracy of the LSSVM model were improved. The training sample set is classified according to the wind speed interval, and the WOA-LSSVM forecasting model is trained by subclass after classification to further improve the accuracy of short-term WPF. The NPKDE method is used to accurately calculate the probability density distribution characteristics of the forecasting error of wind power, and the confidence interval of the WPF is accurately calculated based on the probability density distribution characteristics. The calculation results show that the forecasting accuracy of the WOA-LSSVM model is higher than those of the LSSVM, long short-term memory (LSTM), and particle swarm optimization and least squares support vector machine (PSO-LSSVM) models, and the forecasting accuracy of the WOA-LSSVM model can be further improved after classifying the training sample set. The coverage of the confidence intervals in different time scales is higher than the corresponding confidence level, indicating that the NPKDE method can accurately describe the probability density distribution characteristics of the WPF errors.

A wake fast-calculation model is developed, which can calculate the wind speed distribution of wind farms accurately and efficiently under varying wind speed and wind direction. Based on the wake fast-calculation model, a wind farm optimal controlling model is established to optimize the axial induction factors of wind turbines solving by particle swarm optimization (PSO) algorithm. In this way, the overall wind farm power output can be maximized and the wake losses can be minimized. Horns Rev wind farm in Denmark is selected as the case study, and the calculation results show that the wind farm optimal control algorithm based on the wake fast-calculation model is effective.