Abstract: The uncertainty of wind speed makes it more difficult to predict wind speed,and wind energy is difficult to be used effectively. In order to solve the above problems,a hybrid depth learning model for wind speed interval prediction is proposed based on Convolutional Neural Network（CNN）,Shared Weight Long Short-Term Memory Network（SWLSTM）,Attention Mechanism（AM）and Gaussian Process Regression（GPR）. Firstly,the network combined CNN and SWLSTM is used to extract the features of wind speed series. Secondly,AM module is added to make use of the feature vector. Finally,the interval prediction is carried out through GPR. The model is applied to two wind speed data sets to test,and compared with other wind speed prediction models from two aspects of point prediction accuracy and interval prediction results. The experimental results show that the prediction model can obtain highprecision prediction results and appropriate prediction interval.