A Wind Power Cleaning and Prediction Model based on DBSCAN-RNN-BiLSTM

To address the problems of incomplete cleaning of abnormal power data and low prediction accuracy in wind power prediction, this paper proposes a wind power cleaning and prediction model based on DBSCAN-RNN-BiLSTM. First, the data were classified into normal and abnormal categories using the Density-Based Spatial Clustering of Applications with Noise(DBSCAN) algorithm. Then, the Recurrent Neural Network (RNN) is trained using the delineated normal data and the abnormal power is corrected on the basis of the trained model. Finally, the cleaned power data is temporalized and wind power prediction is performed using a Bidirectional Long Short-Term Memory Network (BiLSTM). The experimental results show that the method proposed in this paper can improve the quality of wind power data and increase the accuracy of wind power prediction.