Wind power forecasting using emotional neural networks

Emotional neural network (ENN) is a recently developed methodology that uses simulated emotions aiding its learning process. ENN is motivated by neurophysiological knowledge of the human´s emotional brain. In this paper, ENNs are developed and examined for prediction tasks. Genetic algorithm is applied for optimal tuning of crisp numerical parameters of ENN. The performance of the proposed ENN is examined using data sets for a couple of synthetic (with constant and variable noise) and real world (wind farm power generation data) case studies. A traditional artificial neural network (ANN) is also implemented for comparison purposes. Numerical results indicate the superiority of ENN over ANN in terms of accuracy and stability.