Accurate wind speed prediction is a essential for enhanced wind energy integration with grid. A hybrid forecasting model is implemented to improve prediction accuracy. Decomposition technique is utilized to separate the input training wind speed data into intrinsic mode functions (IMFs). Deep neural network is used for the feature learning from each sub-series signal. Thus, the developed approach is tested with National Institute of Wind Energy (NIWE) dataset. Experimental evaluation in terms of statistical indices confirms that proposed hybrid model outperforms the existing benchmark approaches.
Wind speed prediction using hybrid long short-term memory neural network based approach
21.01.2021
574601 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Ego-Vehicle Speed Prediction Using a Long Short-Term Memory Based Recurrent Neural Network
Springer Verlag | 2019
|Ego-Vehicle Speed Prediction Using a Long Short-Term Memory Based Recurrent Neural Network
Online Contents | 2019
|