Abstract: In mid-long term wind speed prediction,dealing with the relevant factors correctly is the key point to improve the prediction accuracy.A new prediction scheme that uses rough set method was presented.The key factors that affect the wind speed prediction were identified by rough set theory.Then the rough set neural network prediction model was built by adding the key factors as the additional inputs to the pure chaos neural network model.To test the approach,the data from a wind farm of Heilongjiang province were used.The prediction results were presented and compared to the chaos neural network model and persistence model.The results show that the prediction accuracy of rough set method is the best,and rough set method is a useful tool in mid-long term wind speed prediction.