Medium-to long-term wind power forecasting method based on the CNN-Informer model
To address the uncertainty issues in medium-to long-term wind power forecasting,a method based on the CNN-Informer model is proposed.This method utilizes convolutional neural networks(CNN)to extract long-term sequence features and trends from wind power data,combined with the Informer model for power prediction.The main process of the study involves first correcting missing values and outliers in the collected wind power data using a random forest imputation method.Then,the Pearson correlation coefficient is used to analyze and identify key factors influencing wind power.Finally,experimental validation and result analysis are conducted.The experimental results show that the proposed CNN-Informer model performs better in evaluation metrics such as Root Mean Square Error(RMSE)and R2 compared to the standalone Informer model,demonstrating the effectiveness of this method in improving the accuracy of medium-to long-term wind power forecasting.Future research can further explore the model's adaptability under different conditions and introduce new technologies to continue enhancing prediction accuracy.
medium-to long-term wind power forecastingInformer modelconvolutional neural network(CNN)
万方数据
