Prediction of Wind Speed by Using Chaotic Approach: A Case Study in Istanbul

Abstract

Renewable energy sources have gained great popularity due to the increasing importance given to a sustainable environment and economic development. Because of the environmental friendliness of renewable energy compared to fossil fuels, the tendency and investments in this field have increased. Wind energy comes into prominence among renewable energy sources because of its potential power that is used in various areas currently. Wind energy having stochastic nature is more sensitive to the extreme values of wind speed. Therefore, in order to create wind energy effectively, an accurate wind speed forecast is needed. In this study, nonlinear dynamical system approaches have been implemented by using reconstructing of phase space based on specifying minimum embedded dimension and delay time. In order to find out performance, different error metrics (MSE, RMSE, MAE, and MAPE) have been implemented. According to results, RMSE has been found 0.47 and 0.85 in hourly and daily dataset, respectively. Also, the correlation coefficient between the measurement and the obtained data set was as high as 0.92 in the hourly wind variable. In addition, a lesser correlation coefficient of 0.62 was found in the daily wind speed.

Keywords

• Energy
• Chaos Theory
• Wind Speed
• Turkey

References

1. Baydaroǧlu, Ö., Koçak, K. (2014). SVR-based prediction of evaporation combined with chaotic approach. Journal of Hydrology. https://doi.org/10.1016/j.jhydrol.2013.11.008
2. Bergé, P., Pomeau, Y., Vidal, C. (1984). Order Within Chaos, John Wiley & Sons.
3. Brzozowska, E., Borowska, M. (2016). Selection of phase space reconstruction parameters for EMG signals of the uterus. Studies in Logic, Grammar and Rhetoric. https://doi.org/10.1515/slgr-2016-0046
4. Cassola, F., Burlando, M. (2012). Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output. Applied Energy. https://doi.org/10.1016/j.apenergy.2012.03.054
5. Fraser, A. M., Swinney, H. L. (1986). Independent coordinates for strange attractors from mutual information. Physical Review A, 33(2): 1134-1140. https://doi.org/10.1103/PhysRevA.33.1134
6. Governorship of Istanbul, (n.d). Asya ve Avrupa’yı Birleştiren Şehir. Retrieved from: http://www.istanbul.gov.tr/
7. Hegger, R., Kantz, H., Schreiber, T. (1999). Practical implementation of nonlinear time series methods: The TISEAN package. Chaos. https://doi.org/10.1063/1.166424
8. Jamil, M., Zeeshan, M. (2019). A comparative analysis of ANN and chaotic approach-based wind speed prediction in India. Neural Computing and Applications. https://doi.org/10.1007/s00521-018-3513-2

9. Karakasidis, T. E., Charakopoulos, A. (2009). Detection of low-dimensional chaos in wind time series. Chaos, Solitons and Fractals. https://doi.org/10.1016/j.chaos.2008.07.020
10. Kennel, M. B., Brown, R., Abarbanel, H. D. I. (1992). Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical Review A. https://doi.org/10.1103/PhysRevA.45.3403
11. Kliková, B., Raidl, A. (2011). Reconstruction of Phase Space of Dynamical Systems Using Method of Time Delay. Proceedings of the 20th Annual Conference of Doctoral Students - WDS 2011.
12. Koçak, K., Şaylan, L., Eitzinger, J. (2004). Nonlinear prediction of near-surface temperature via univariate and multivariate time series embedding. Ecological Modelling. https://doi.org/10.1016/s0304-3800(03)00249-7
13. Miraji, M. M. (2015). Chaotic Analysis of Wind Regime [MSc. Thesis, Istanbul Technical University]. Energy Institute. http://hdl.handle.net/11527/17987
14. Özgür, E. (2010). Kaotik yaklaşımla rüzgar hızı öngörüsü [Wind speed prediction with chaotic approach]. [BSc. thesis, Istanbul Technical University].
15. Özgür, E., Koçak, K. (2011). Kaotik Yaklaşımla Kısa Vade Rüzgar Hızı Öngörüsü. V. Atmosfer Bilimleri Sempozyumu, Istanbul, Turkey. (in Turkish)
16. Özgür, E., Koçak K. (2016). Investigation of average prediction time for different meteorological variables by using chaotic approach. EGU General Assembly 2016, Vienna, Austria.
17. Sánchez, I. (2006). Short-term prediction of wind energy production. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2005.05.003
18. Takens, F. (1981). Detecting strange attractors in turbulence. Dynamical systems and turbulence, Warwick 1980(pp. 366–381). Springer-Verlag Berlin Heidelberg.
19. Vaheddoost, B., Koçak, K. (2019). Temporal dynamics of monthly evaporation in Lake Urmia. Theoretical and Applied Climatology. 137(3), 2451-2462.
20. Yildirim, H. A., Altinsoy, H. (2018). Nonlinear dynamics of monthly temperature data set in the Northwestern (Marmara region) Turkey. International Journal of Global Warming. https://doi.org/10.1504/IJGW.2018.088647
21. Yilmaz, M., Gümüş, B., Kiliç, H., Asker, M. E. (2017). Chaotic analysis of the global solar irradiance. 6th International Conference on Renewable Energy Research and Applications, ICRERA 2017. https://doi.org/10.1109/DISTRA.2017.8191219
22. Wilczak, J., Finley, C., Freedman, J., Cline, J., Bianco, L., Olson, J., Djalalova, I., Sheridan, L., Ahlstrom, M., Manobianco, J., Zack, J., Carley, J. R., Benjamin, S., Coulter, R., Berg, L. K., Mirocha, J., Clawson, K., Natenberg, E., Marquis, M. (2015). The wind forecast improvement project (WFIP): A public-private partnership addressing wind energy forecast needs. Bulletin of the American Meteorological Society. https://doi.org/10.1175/BAMS-D-14-00107.1
23. Wind Energy International (WWEA). (2020). “Total Installed Capacity”. Retrieved from https://library.wwindea.org/global-statistics/