Recent trends on artificial neural networks for prediction of wind energy

Abstract

A variety of Artificial Neural Network models for prediction of hourly wind speed (which a few hours in advance is required to ensure efficient utilization of wind energy systems) is studied and the results are compared. Results in terms of simulation and prediction are obtained with Feed Forward Back Propagation Neural Networks (FFBPNN) which shows its performance better than other neural networks. Empirical relationship is developed which shows the Gaussian profile for the number of neurons which varies with lag inputs, that is, nn = k exp(-il2) where nn shows the number of neurons, il the lag inputs, and k the sloping ratio. Feed Forward Neural Networks (FFNNs) can be corrected with optimization of our suggested relationship for simulators followed by back propagation technique. Key words: Artificial Neural Network, McCulloch-Pitts neurons, Feed Forward Back Propagation Neural Networks, Empirical relationship for neurons, Markov Transition Matrix, Artificial Neural Fuzzy Information System.