A Novel Wind Speed Forecasting Framework Using Data Preprocessing Based Adversarial Approach

Abstract

Wind energy generation, which has significant economic, social, and environmental benefits, requires accurate wind speed prediction. Due to the unpredictability and intermittency of wind, a robust methodology is essential for forecasting precise wind speeds. Addressing the challenges, this research proposes a hybrid and novel approach for accurate wind speed forecasting. The proposed method is split into data decomposition using robust complete ensemble empirical mode decomposition with adaptive noise, and wind speed prediction using adversarial approach. In the wind speed prediction, two robust forecasting models, convolutional neural network, and long short-term memory are adopted and trained in adversarial manner to enhance the prediction of wind speed. Long short term memory network functions as the generator which predicts the wind speed effectively for 1 h ahead wind speed prediction. Convolutional neural network model acts as a discriminator which enhances the forecasting performance of the generator. Various performance metrics are adopted to examine the performance of the proposed approach for 1 h ahead prediction, and the metrics are also compared to eight reference wind speed prediction models. The experimental findings demonstrate that the proposed adversarial hybrid model improved 25% over the comparative predictive models.