LAUSR

Wind speed forecasting is still a challenge due to the stochastic and highly varying characteristics of wind. In this paper, a graph deep learning model is proposed to learn the powerful spatio-temporal features from the wind speed and wind direction data in neighboring wind farms. The underlying wind farms are modeled by an undirected graph, where each node corresponds to a wind site. For each node, temporal features are extracted using a long short-term memory Network. A scalable graph convolutional deep learning architecture (GCDLA), motivated by the localized first-order approximation of spectral graph convolutions, leverages the extracted temporal features to forecast the wind-speed time series of the whole graph nodes. The proposed GCDLA captures spatial wind features as well as deep temporal features of the wind data at each wind site. To further improve the prediction accuracy and capture robust latent representations, the rough set theory is incorporated with the proposed graph deep network by introducing upper and lower bound parameter approximations in the model. Simulation results show the advantages of capturing deep spatial and temporal interval features in the proposed framework compared to the state-of-the-art deep learning models as well as shallow architectures in the recent literature.