Using AWPSO to Solve the Data Scarcity Problem in Wind Speed Prediction by Artificial Neural Networks

A new strategy in wind speed prediction based on adaptive weighted particle swarm optimization combined with artificial neural networks was proposed. Regarding the data gathering, sometimes it is difficult to provide the neural network with sufficient data to be trained efficiently. In order to solve this problem Adaptive weighed particle swarm optimization is used to increase the data the produced data is fed to a multilayered feed forward neural network to predict the future wind speed. This method has lead to good estimated wind speed accuracy and good prediction performance.