Wind speed and wind power forecasting technology are key measures to strengthen the management of integration of wind power. In order to improve the accuracy of short-term wind forecasting and reduce the impact of wind power grid on power quality and safe and stable operation of power system , a short term wind speed prediction model based on chaotic time series using support vector machine is proposed. In this model, short-term wind speed prediction is conducted by using least squares support vector machine under the Bayesian framework based on the modeling of chaotic time series of wind speed. Simulation results show that the proposed model can effectively improve the accuracy of short term wind speed prediction.