Application of waikato environment for knowledge analysis based artificial neural network models for wind speed forecasting

Abstract

The installation of wind turbine in a particular location in India is based on the wind speed prediction. The wind speed can be predicted using different models. The maximum temperature, average temperature, minimum temperature, ambient temperature, dew-point temperature, atmospheric pressure, air pressure, vapor pressure, solar radiation, altitude, longitude, wind direction, mean sea level, relative humidity, time of the day, water vapor, wind power are the input variables to the artificial neural network (ANN) model which affects the accuracy of the wind speed prediction. Therefore, the selection of the most relevant input variables to the ANN model is necessary. With this objective, InfoGain Attribute Evaluator with Ranker Search Method using WEKA (a data mining implementation) is applied to find the most relevant input variables. Identified 8 relevant input variables are used as input to ANN model to predict the wind speed. The results obtained validates that the combination of input variables selected through InfoGain Attribute Evaluator gives higher prediction accuracy than any other combination of input variables. This method is used to predict the wind speed of wind turbine in Rajasthan, north-west region of India.