The accurate prediction of Wind Energy Speed (WES) is very important and essential for monitoring, controlling, planning and distribution of generated power to meet consumers need due to the shortage in electricity supply in Abuja. This study investigates the Artificial Neural Network (ANNs) method for the implementation of Support Vector Machine (SVM) algorithm, for classification, regression, and outlier detection for the forecasting of wind speed from local meteorological training data gotten from the Nigerian Meteorological agency (NiMET), National Weather Research Center, located at Nnamdi Azikiwe International Airport, Bill Clinton Dr, 900102, Abuja, Nigeria from a period of over thirty years (1983-2013). The dataset is carefully pre-processed to handle missing values and outliers. The experimental results demonstrate that the SVM model outperforms alternative methods in terms of wind speed prediction accuracy. The findings of this research highlight the efficacy of SVM in wind speed prediction, showcasing its potential for practical implementation in wind energy systems.