Reducing carbon emissions has accelerated the use of various renewable resources for electricity generation. Wind generation, in this context has seen increasing installations globally. Managing the intermittency of wind towards existing power system operation and control therefore becomes crucial. One effective solution is to predict the future values of wind power production. This paper focuses on the improvement of the present forecasting methods and reduction of the forecasting error. This paper uses Auto Regressive Moving Average (ARMA) to predict wind speed. However, order estimation of ARMA is a crucial issue. Artificial Neural Network (ANN) has been used for parameter estimation, which is then combined with Akaike Information Criteria (AIC) for order estimation. A simulation study has been conducted by comparing the proposed hybrid results with Genetic Algorithm (GA) for parameter estimation and an exhaustive search for order estimation.