Genetic Fuzzy Learning of local wind conditions

Abstract

The wind climate measured in a point could be

described as the regional wind climate of the zone forced by local

effects derived from topography, roughness and obstacles in the

surrounding area. This paper presents a method that allows to find

fuzzy relations between the local wind climate in a location and the

physical geography of the area. The fuzzy sets used in this work

will connect relief elements with a probability relationed with the

chances of flow over the concerned element. Thus, evaluating the

heights and slopes of the terrain around the selected point, each

fuzzy system will generate a possible local wind climate, which will

be compared with the real one. In order to obtain the best

agreement, a population of these fuzzy systems will be improved

using Genetic Algorithms.