A hybrid forecasting model based on artificial neural network and teaching learning based optimization algorithm for day-ahead wind speed prediction

Abstract

In this analytical study, a hybrid day-ahead wind speed prediction approach for high accuracy is implemented. The hybrid approach initially converts raw wind speed data series into actual hourly input structure for reducing uncertainty and the intermittent nature of wind speed. The back-propagation neural network is utilized for its better learning capability and also for its ability for nonlinear mapping among complex data. The teaching learning-based optimization algorithm is used to auto-tune the best weights of the artificial neural network. This optimization algorithm is used for its powerful ability to search and explore on a global scale. Then, the artificial neural network teaching learning-based optimization approach is implemented for wind speed forecasting. After that, the day-ahead prediction is performed using the proposed hybrid model for actual hourly input structure. The hybrid model prediction results give enhanced prediction accuracy when compared to existing approaches.