A hybrid wind speed forecasting model using complete ensemble empirical decomposition with adaptive noise and convolutional support vector machine

Abstract

Wind energy is a clean, green energy source that is used effectively in power system grids. Wind forecasting is the key requirement for enhanced integration. Wind speed forecasting is more challenging due to the unpredictable and intermittent nature of the wind. As a result, a robust and novel frame-work is proposed by hybridizing complete ensemble empirical decomposition with adaptive noise (CEEMDAN), convolutional neural network (CNN), and support vector machine (SVM). The CEEMDAN algorithm is used to remove noise from the raw data. Then, to extract the dominating characteristics from the noiseless wind speed data, CNN is used. Finally, SVM forecasts the wind speed. The hybridization of CNN and SVM enhanced the computational efficiency as well as the performance. For comparative analysis, six different state-of-the-art forecasting approaches are employed. An experimental study is carried out utilising real-time 5-minute interval data obtained from Manhattan's Garden City. The proposed framework performance is assessed through various statistical metrics. With relatively low error metrics and higher R2 score, the proposed framework outperformed all other comparative models, according to the experimental results.