Evaluation of Optimal Fuzzy Membership Function for Wind Speed Forecasting


1 Electrical Engineering Department, Central Tehran Branch, Islamic Azad University, Tehran, Iran.

2 Electrical Engineering Department, Tehran South Branch, Islamic Azad University, Tehran, Iran.


In this paper, a new approach is proposed in order to select an optimal membership function for inputs of wind speed prediction system. Then using a fuzzy method and the stochastic characteristics of wind speed in the previous year, the wind speed modeling is performed and the wind speed for the future year will be predicted. In this proposed method, the average and the standard deviation of inputs data are calculated. The membership function shape and the domain intervals are evaluated using the variance of system. This technique prevents from trial and error method for defining the shape and domain intervals of optimal membership function and helps to achieve the desired prediction in a quick way. The wind speed is estimated in the fuzzy inference system and simulated with the fuzzy logic. The sensitivity analyses are performed by changing the input parameters and membership functions shape and the results are compared. The results demonstrate that this new prediction method is a fast and applicable method compared to the other methods since the calculated error will be more than the error of this method if the shape and domain interval of membership function are changed


[1] Burton T, Sharpe D, Jenkins N, Bossanyi E., “Wind Energy Handbook”, John Wiley and Sons, 2001.
[2] R. Billiton, and L. Gan, “Wind Power Modelling and Application in Generating Adequacy Assessment”, WESCANEX 93 Communication Computers and Power in the Modern Environment, Conference Proceedings, pp. 100-106, 1993.
[3] R. Karki, P. Hu, and R. Billinton, “Reliability evaluation of a wind power delivery system using an approximate wind model”, Proceedings of the 41st International Universities Power Engineering Conference (UPEC 06), pp. 113-117, 2006.
[4] A. V. Machias, and G. D. Skikos, “Fuzzy Risk Index of Wind Sites,” IEEE Transactions on Energy Conversation, Vol. 7, No. 4, pp. 638-643, 1992.
[5] H. Nachtmann, and J. R. Chimka, “Fuzzy Reliability in Conceptual Design”, Annual Reliability & Maintainability Symposium, pp. 360-364, 2003.
[6] M. Mohandes, S. Rehman, and S. M. Rahman,“Estimation of Wind Speed Profile Using Adaptive Neuro-Fuzzy Inference System (ANFIS)”, Applied Energy, Vol.88, No.11, pp. 4024-4032, 2011.
[7] F. J. Chang, and Y. T. Chang, “Adaptive Neuro-Fuzzy Inference System for Prediction of Water Level in Reservoir”, Advances in Water Resources, Vol.29, No.1, pp. 1-10, 2006. [8] L. X. Wang, and M. Jerry, “Generating fuzzy rules by learning from examples”, IEEE Transactions on Systems, Man, and Cybernetics, Vol.22, No.6, pp. 1414-1427, 1992.