Estimation of wind power generation using neural networks

Abstract EN

This paper uses data collected by weather stations to develop a neural network solution for extrapolation of wind speeds at heights ranging.

Work aims to improve the foundations for a prediction of a wind profile of quality, at short and long terms.

This paper begins with a comparison between different actual methods of extrapolation wind speed, and then describes an artificial neural network (ANN) approach for the vertical wind speed extrapolation.

The outputs of models are compared with the real measured data so the results show a significant improvement.

We conclude with the improvement of results when the assumed SISO (single-input-single-output) system is considered as a non-linear multi variable system.