Introducing a Hybrid Method for Estimating Wind Speed Using Information from Neighboring Stations in Isfahan Province

Document Type : Research Paper

Authors

1 Irrigation & Reclamation Engrg. Dept. University of Tehran Karaj, Iran.

2 Zahra Shariatmadari Assistant Prof., Irrigation & Reclamation Engrg. Dept. University of Tehran Karaj, Iran.

Abstract

The prediction of wind components including wind speed is one of the important factors, especially in the case of evaporation in a watershed. In this paper, in order to increase the efficiency of support vector machines (SVM) for predicting wind speed, the SVM model was combined with the firefly optimization algorithm called hybrid model (HM). In this regard, the wind speed data from synoptic stations of Isfahan province were used to estimate the monthly wind speed values of the unknown neighboring stations. Then, the efficiency of the SVM and HM models was compared. Finally, the RMSE, MAE, WI, and NS indices were used to evaluate the both models performance efficiency.  The results in the evaluation step showed that the hybrid model (HM) with high correlation and lower error values has higher performance efficiency as compared to the SVM model. as Also, the method of using neighboring stations data as inputs for the predictive models of unknown station is a proper method for estimation of wind speed.

Keywords

Main Subjects

References

Afkhami, H., Talebi, A., Mohammadi, M. and Fotouhi, F. (2015). Investigation of the feasibility of wind speed prediction using hybrid model of neural networks, neural -fuzzy networks and wavelet (Case Study: Station of Yazd). jwmseir. 9 (30): 31-40. (In Farsi)
Alexiadis, M. C., Dokopoulos, P. S. and Sahsamanoglou, H. S. (1998). Short-term forecasting of wind speed and related electrical power.Solar Energy. 63(1): 61-68,1998.
Burton, T., Sharpe, D., Jenkins, N. and Bossanyi, E. (2001). Wind energy handbook. Chichester: John  Wiley and Sons.
Cadenas, E. and Rivera, W. 2007. Wind speed forecasting in the south coast of Oaxaca, Mexico. Renewable Energy. 32 (12): 2116-2128.
Deo, R., Ghorbani. M.A., Samadianfard, S., Maraseni, T., Bilgili, M. and Biazar, M. (2017). Multi-layer        perceptron hybrid model integrated with the firefly optimizer algorithm for wind speed prediction of target site using a limited set of neighboring reference station data. Renewable Energy. 116: 309-323.
Damousis, I. G. and Dokopoulos, P. A. (2001). Fuzzy expert system for the forecasting of wind speed           and power generation in wind farms. In Proceedings of the IE IEEE International Conference on Power Industry Computer Applications PICA 01. 63–69.
Ghorbani, M. A., Deo, R., Yaseen, Z.M., Kashani, M.H. and Mohammadi, B. (2017a). Pan evaporation       prediction using a hybrid multilayer perceptron-firefly algorithm (MLP-FFA) model: case    study in North Iran. Theoretical and Applied Climatology. 129:1-13.
Ghorbani, M. A., Shamshirband, SH., Zare Haghie, D., Azania, A., Bonakdarif, H. and Ebtehajf, I. (2017b).               Application of firefly algorithm-based support vector machines for prediction of field    capacity and permanent wilting point. Soil & Tillage Research. 172: 32–38.
Guangdian, G.W. and Zhijie, D. (1994). Wind pattern recognition in neural fuzzy wind turbine         control system. NAFIP, IFIS, NASA The Industrial Fuzzy and Intelligent Systems Conference and the NASA Joint Technology. 381-5 p.
Hosseini-Moghari, S.M. and Banihabib, M.E. (2014). Optimizing operation of reservoir for agricultural water supply using firefly algorithm. Journal of  Water and Soil Resources Conservation. 3(4). (In Farsi)
Kazemzadeh, M,J., Daneshmand. and Ahmadfard, M. A. (2015). Optimal Remediation Design of Unconfined Contaminated Aquifers Based on the Finite Element Method and a Modified Firefly Algorithm. Water Resources Management. 29(8): 2895-2912.
Kisi, O., Genc. O., S. Dinc and M. Zounemat-Kermani. (2016). Daily pan evaporation modeling using chi-squared automatic interaction detector, neural networks. Classification and Regression tree Computers and Electronics in Agriculture. 122: 112–117.
Kisi, O., Shiri, J., Karimi, S., Shamshirband, Sh., Motamedi, Sh., Petkovic, D. and Hashim, R. (2015). A survey of water level fluctuation predicting in Urmia Lake using support vector machine with firefly algorithm. Applied Mathematics and Computation. 270: 731-743.
Liu, H., Tian, H. and Li, Y. (2012a). Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction. Applied Energy. 98, 415-424.
Liu, H., Chen, C., Tian, H. and Li., Y. (2012b). A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks. Renewable Energy. 48: 545-556.
Mohammadi, B. (2017). Daily Evaporation prediction based on a hybridization  of  Artificial Neural Network and firefly Optimization Algorithm. Thesis is approved for the degree of Master of Science in Water Resources. Department of Water Engineering, Faculty of Agriculture, University of Tabriz. (In Farsi)
Mohammadi, B. and Emamgholizadeh, S. (2017). Using principal component analysis to inputs the effective rainfall estimates based on entries to help support vector machine and artificial neural network. Journal of  Rainwater Catchment Systems. 4(4): 67-75. (In Farsi)
Mohammadi, B., Moazenzadeh, R. (2017).  Uncertainty analysis of  artificial neural network models and support vector machine in rainfall estimation. Journal of  Rainwater Catchment Systems. 5(1): 43-50. (In Farsi)
Oztopal,  A. (2006). Artificial neural network approach to spatial estimation of wind velocity data. Energy Conversion and Management. 47(4): 395-406.
Pai, PF. and Hong, WC. (2007). A recurrent support vector regression model in rainfall forecasting.                Hydrological Process, 21:819-827.
Philippopoulos, K. and Deligiorgi, D. (2012). Application of artificial neural networks for the spatial estimation of  wind speed in a coastal region with complex topography. Renewable Energy. 38(1): 75-82.
Potter, C. W. and Negnevitsky, M. (2006). Very short-term wind forecasting for Tasmanian power generation. IEEE Transaction on power systems. 21(2): 965-972.
F. Rahimzadeh, A. M., Noorian, M., Pedram, and  Kruk, M. C.(2011). Wind speed variability over Iran and its impact on wind power potential: A case study for Esfehan Province,” Meteorol. Appl., METEOROLOGICAL APPLICATIONS Meteorol. Appl. 18: 198–210.
Soder, L.  (2004). Simulation of wind speed forecast errors for operation planning of multi-area power          systems. 8th International conference on probabilistic methods applied to power systems. Iowa state university. Iowa. 23-28p.
Vapnik,V. N. (1998). Statistical Learning Theory. Wiley, New York.
Watson, S. J., Landberg, L. and Halliday, J.A. (1994). Application of wind speed forecasting to the                integration of wind energy in to a large scale power system. In: IEE Proceedings of            Generation, Transmission and Distribution, 141(4): 357-362.
Yang, X.S. (2009). Firefly algorithms for multimodal optimization. In International symposium on stochastic algorithms. Springer, Berlin, Heidelberg. Pp: 169-178.
Yang, X. S. and He, X. (2013). Firefly algorithm: recent advances and applications. International Journal of Swarm Intelligence. 1(1): 36-50.
Yoon, H., Jun, S. C., Hyun, Y., Bae, G. O. and Lee, K. K. (2011). A comparative study of artificial neural     networks and support vector machines for predicting groundwater levels in a coastal aquifer.    Journal of Hydrology. 396:128–138.
Zhang, Q. and Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks. 3(6): 889-898.
 
Iranian Journal of Soil and Water Research
Volume 50, Issue 1
March and April 2019
Pages 177-188

Files

Share

How to cite

Statistics