A Comparative Study of Adaptive Neuro Fuzzy Inference System and Support Vector Regression for Forecasting Wind Power

Abstract

The forecast of the power generated by a wind power plant is a process that wind farm companies need to do every day. Electrical system manager uses these forecasts to plan the next day’s electrical generation. Thus, while generation-consumption balance in the grid is maintained, numbers of reserve power plants are decreased. Wind power has uncertainty as it depends on nature. Therefore, wind speed forecasts and wind direction forecasts of the power plant area are generally used in wind power forecasts. In this study, hourly wind power generation of next day is forecasted by using Adaptive Neuro Fuzzy Inference System (ANFIS) and Support Vector Regression (SVR) methods. The hour of day, wind speed forecast and wind direction forecast are the inputs of the forecast system. One-year data are selected as training data, six-mount data are forecasted. Five different models are formed by using the system inputs in different configurations and final forecast are found by averaging the model forecasts. The average normalized mean absolute error values are found 10.86% and %10.8 with ANFIS and SVR, respectively. 

Keywords

• Adaptive Neuro Fuzzy Inference System,ANFIS,Energy management,Support Vector Regression

References

1. [1] Annual Energy Outlook, U.S. Energy Information Administration, 2018, Available: https://www.eia.gov/outlooks/aeo/
2. [2] Renewable energy - European commission website, 2018, [Online]. Available: https://ec.europa.eu/energy/en/topics/renewable-energy.
3. [3] Federal energy management program – Office of energy efficency & reneable energy, 2017 [Online]. Available: https://energy.gov/eere/femp/achieving-30-renewable-electricity-use-2025.
4. [4] Global wind report 2017 - Global Wind Energy Council website, 2017, [Online]. Available: http://www.gwec.net/publications/global-wind-report-2/
5. [5] F. Fazelpour, N. Tarashkar and M. A. Rosen, “Short-term wind speed forecasting using artificial neural networks for Tehran, Iran”, International Journal of Energy and Environmental Engineering, vol. 7(4), pp. 377-390, 2016.
6. [6] Zhang, Yao, Jianxue Wang, and Xifan Wang. "Review on probabilistic forecasting of wind power generation.", Renewable and Sustainable Energy Reviews, vol. 32, pp. 255-270, 2014.
7. [7] A. Dukpa, I. Duggal, B. Venkatesh and L. Chang, “Optimal participation and risk mitigation of wind generators in an electricity market”, IET renewable power generation, vol. 4(2), pp. 165-175, 2010.
8. [8] C. Gallego-Castillo, R. Bessa, L. Cavalcante and O. Lopez-Garcia, “On-line quantile regression in the RKHS (Reproducing Kernel Hilbert Space) for operational probabilistic forecasting of wind power”, Energy, vol. 113, pp. 355-365, 2016.

9. [9] Q Xu, D. He, N.,Zhang, C. Kang, Q. Xia, J. Bai, and J. Huang, “A short-term wind power forecasting approach with adjustment of numerical weather prediction input by data mining”, IEEE Transactions on Sustainable Energy, vol. 6(4), pp. 1283-1291, 2015.
10. [10] Çevik H.H. and Çunkaş M. “Short-term wind power forecasting using ANFIS and regression methods”, 6th International Conference on Advanced Technology & Sciences (ICAT), Riga/Latvia, 12-15 Sep, 2017, pp. 67-71.
11. [11] Zeng, Jianwu, and Wei Qiao. "Support vector machine-based short-term wind power forecasting." Power Systems Conference and Exposition (PSCE), 2011 IEEE/PES. IEEE, 2011.
12. [12] Salcedo-Sanz, S., Ortiz-Garcı, E. G., Pérez-Bellido, Á. M., Portilla-Figueras, A. and Prieto, L., “Short term wind speed prediction based on evolutionary support vector regression algorithms”, Expert Systems with Applications, vol. 38(4), pp. 4052-4057, 2011.
13. [13] N. D. Duy-Phuong, Y. Lee and J. Choi, “Hourly Average Wind Speed Simulation and Forecast Based on ARMA Model in Jeju Island, Korea”, Journal of Electrical Engineering & Technology, vol. 11(6), pp. 1548-1555, 2016.
14. [14] R. Azimi, M. Ghofrani, and M. Ghayekhloo, “A hybrid wind power forecasting model based on data mining and wavelets analysis”, Energy Conversion and Management, vol. 127, pp. 208-225, 2016.
15. [15] S. Wang, N. Zhang, L. Wu, and Y. Wang, “Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method”, Renewable Energy, vol. 94, pp. 629-636, 2016.
16. [16] ST. Hong, P. Pinson and S. Fan, “Global energy forecasting competition 2012”, International Journal of Forecasting, vol. 30(2), 357-363, 2014.
17. [17] J. S. Jang, “ANFIS: adaptive-network-based fuzzy inference system”. IEEE transactions on systems, man, and cybernetics, vol. 23(3), pp. 665-685, 1993.
18. [18] Vapnik, Vladimir. Statistical learning theory. 1998. Vol. 3. Wiley, New York, 1998.
19. [19] Schlkopf, B., and A. Smola. "A tutorial on support vector regression." NeuroCOLT2 Technical Report Series, 1998.
20. [20] M. B. Ozkan and P. Karagoz, "A novel wind power forecast model: Statistical hybrid wind power forecast technique (SHWIP)", IEEE Transactions on Industrial Informatics, vol. 11(2), pp. 375-387, 2015.