A neural network based approach for wind resource and wind generators production assessment

摘要: Abstract The statistical study of wind speed measurements on a site makes it possible to determine distribution law, needed assess the available or recoverable energy potential. classical approach consists in assimilating law standard models, for example Weibull Rayleigh, and determining parameters model so that gets closest discrete obtained by statistically treating measurements. is most used one provides good results. However, accurate determination constitutes major problem. Multi Layer Perceptron type artificial neural networks, highly effective function approximation problems, are here law. characteristics have been determined means compared with those method. results show achieved assessments closer than model. This has enabled potential Dakar be more way. models also amount generator WES18 80 kW power, set up at 10 m 40 above ground, would produce annually.