Short-Term Wind Power Prediction Based on STL-AOA-Transformer Algorithm

Precise short-term wind power forecasting plays a crucial role in ensuring the effective and secure functioning of wind power installations. To improve the accuracy of short-term wind power forecasts, in this paper, a hybrid short-term wind power forecasting model STL-AOA-Transformer based on seasonal and trend decomposition using Loess (STL), arithmetic optimization algorithm (AOA) and transformer is proposed. AOA is used to optimize the parameters of transformer. STL is employed for the purpose of breaking down the initial data into modal components characterized by reduced volatility, in order to effectively capture the data features. These modal components are then fed into the AOA- Transformer for the prediction of short-term wind power and the subsequent derivation of the ultimate forecasted value. The efficacy of the model was assessed through testing and validation using authentic data spanning four seasons and four stations, and compared to three other models. The results show that the model fits the data well and has high prediction accuracy, which has important practical value.