Abstract of Thesis presented at COPPE/UFRJ as a partial fulfillment of the requirements for the degree of Master of Science (M.Sc.)

Application of Neural Networks to Wind Forecasting for a Horizon of 24 Hours

Guilherme Camargo Rodrigues

June/2007

Advisor:

Alexandre Pinto Alves da Silva

Department:

Eletrical Engineering

      This work develops a computer model based on artificial neural networks for wind forecasting considering a horizon of 24 hours. Multi-Layer Perceptrons have been employed, with back-propagation training, and several configurations of networks. Simulations have been performed with real series of wind velocity of the Brazilian south region, presenting better results compared with the ones from methods of persistence.