Integration of wind power into the grid has been rapidly increasing at both the transmission as well as distribution levels. Wind power generation is variable, nonlinear, and intermittent in nature. The monthly average and maximum wind power generation vary over the year. To effectively integrate wind power into the grid, it is vital to provide forecasting for different months. Therefore, the machine learning technique has been applied to forecast the wind power generation for each month separately. Its accuracy, root mean square error (RMSE), mean absolute error (MAE), and standard deviation (SD) of forecasting error have been analyzed for every month and the whole year.