Two critical issues in renewable energy are how to make wind energy cost effective and how to integrate wind energy into electricity grids. Within many approaches to cost reduction, wind speed forecasting was mentioned as an effective approach because accurate forecasting of wind speed has a direct impact on the scheduling of a power system, and also the dynamic control of the wind turbine. This research investigates the practical use of Self Organizing Map (SOM) as a special type of neural network based forecasting method. In this paper, forecasting the average, maximum and minimum of one-day-ahead wind speed based on the past wind speed states of the previous 24 hours is the objective.