Research on short term wind power prediction method based on CNN-LSTM
In the context of China's dual carbon strategy,as a green renewable energy,wind power has been developed rapidly.However,due to the uncertainty of wind power,direct access to the grid will pose a threat to the safe operation of the grid.To this end,it is necessary to accurately predict the short-term wind power so that the power grid can dispatch power from different sources in advance to ensure the smooth operation of the power grid.With the development of deep learning technology,it provides a new way to improve the accuracy of short-term wind power prediction.In order to give full play to the advantages of local feature extraction of Convolutional Neural Network(CNN)and the advantage of time series feature extraction of Long Short-Term Memory Network(LSTM),this paper proposes a new hybrid neural network to predict short-term wind power prediction by combining two neural networks,and explores two different hybrid models:CNN-LSTM parallel model and dual CNN-LSTM model.Experimental results show that compared with the traditional machine learning model,the single LSTM model and the CNN-GRU model in the existing literature,the two hybrid models proposed in this paper have higher prediction accuracy,and the CNN-LSTM model has the highest prediction accuracy,and the two models also have good robustness.
short term wind power predictionconvolutional neural networklong short-term memory networkhybrid neural network model
NETL
NSTL
万方数据
