Wind Energy Modelling and Machine Learning Approach to Study Wind Direction Effect
DOI:
https://doi.org/10.53560/PPASA(62-3)698Keywords:
Weibull Distribution, Wind Energy Modelling, Python Programming, Least Squares Method, Machine Learning, Artificial Neural Networks (ANN), Wind DirectionAbstract
Wind energy is one of the green renewable energy sources that is available everywhere. The wind-generated electrical energy is much less than the available wind potential. No windmill can even harness 50% of the available wind energy. A lot of research investigations are still needed to explore and harness the maximum energy from wind potential. This work is one of such series of research, in which we modeled wind speed using the Weibull distribution through a Python program that uses the least square method based on Python built-in functions and evaluated the shape and scale parameters of the distribution. The program also compares parameters calculated by other existing methods. The Python program based on the least square method fits the Weibull distribution well compared to the existing methods. The maximum value of scale parameters was found in June (more than 6.2), the corresponding value is also close in May, where it is more than 6.1; the other two months that follow June and May (July and September) have scale parameters near 5.7. It shows that the wind potential is maximum in June, and reasonable wind energy is available in May, July, and September. The effect of wind direction on the modelling of wind speed is also investigated. Perhaps it is the first study that involves wind direction in wind speed modelling. Two different Artificial Neural Network Architectures were studied with and without wind directions in the input. It was found that the results improve if wind direction is also taken in the list of input parameters. The Root Mean Square Error is the least (RMSE = 0.7224) for the model which includes wind direction in the input layer, the performance indicator (0.5219) is also the best for this architecture as compared to the other three.
References
1. Z. Elahi, W. Gull, and Z. Uddin. Weibull distribution parameter estimation using spreadsheets. Spreadsheets in Education 1: 1-12 (2023). https://sie.scholasticahq.com/article/72617
2. M. Zahid, A. Rajput, S. Rehman, M. Adeel, and Z. Uddin. A computer package to model wind speed distribution using six different methods including maximum entropy principle. International Journal of Energy 45(3-4): 207-218 (2024).
3. J.K. Khan, M. Shoaib, Z. Uddin, I.A. Siddiqui, A. Aijaz, A.A. Siddiqui, and E. Hussain. Comparison of wind energy potential for coastal locations: Pasni and Gwadar. Journal of Basic & Applied Sciences 11: 211-216 (2015).
4. J.K. Khan, F. Ahmed, Z. Uddin, S.T. Iqbal, S.U. Jilani, A.A. Siddiqui, and A. Aijaz. Determination of Weibull parameter by four numerical methods and prediction of wind speed in Jiwani (Balochistan). Journal of Basic & Applied Sciences 11: 62-68 (2015).
5. J.K. Khan, Z. Uddin, I.S. Tanweer, F. Ahmed, A. Aijaz, and S.U. Jilani. An analysis of wind speed distribution and comparison of five numerical methods for estimating Weibull parameters at Ormara, Pakistan. European Academic Research II (11): 14007-14015 (2015).
6. Z. Uddin, and N. Sadiq. Method of quartile for determination of Weibull parameters and assessment of wind potential. Kuwait Journal of Science 50(3A): 105-119 (2023).
7. A.A. Rajput, M. Daniyal, M.M. Zahid, H. Nafees, M. Shafi, and Z. Uddin. New approach to calculate Weibull parameters and comparison of wind potential of five cities of Pakistan. Advances in Energy Research 8(2): 95 (2022).
8. S.U. Rehman, N. Sadiq, I. Tariq, M.M. Khan, M.M. Zahid, A.A. Rajput, and Z. Uddin. A new mathematical technique and its Python program to assess wind potential. Beni-Suef University Journal of Basic and Applied Sciences 13(1): 61 (2024).
9. Z. Uddin, M. B. Khan, M.H., Zaheer, W. Ahmad, and M.A., Qureshi. An alternate method of evaluating Lagrange multipliers of MEP. SN Applied Sciences 1: 224 (2019).
10. N. Sadiq. Seasonal and continual wind speed modelling for the coastal urban city, Karachi. MAUSAM 69(2): 289-296 (2018).
11. M.A. Ghorbani, R. Khatibi, M.H. FazeliFard, L. Naghipour, and O. Makarynskyy. Short-term wind speed predictions with machine learning techniques. Meteorology and Atmospheric Physics 128: 57-72 (2016).
12. H. Demolli, A.S. Dokuz, A. Ecemis and M. Gokcek. Wind power forecasting based on daily wind speed data using machine learning algorithms. Energy Conversion and Management 198: 111823 (2019).
13. Q. Zhu, J. Chen, L. Zhu, X. Duan, and Y. Liu. Wind speed prediction with spatio–temporal correlation: A deep learning approach. Energies 11(4): 705 (2018).
14. S. H. Hur. Short-term wind speed prediction using Extended Kalman filter and machine learning. Energy Reports 7: 1046-1054 (2021).
15. R. Li and Y. Jin. A wind speed interval prediction system based on multi-objective optimization for machine learning method. Applied Energy 228: 2207-2220 (2018).
16. B.M.A. Ehsan, F. Begum, S.J. Ilham, and R.S. Khan. Advanced wind speed prediction using convective weather variables through machine learning application. Applied Computing and Geosciences 1: 100002 (2019).
17. Y.S. Türkan, H.Y. Aydoğmuş, and H. Erdal. The prediction of the wind speed at different heights by machine learning methods. An International Journal of Optimization and Control: Theories & Applications (IJOCTA) 6(2): 179-187 (2016).
18. M.S. Hanoon, A.N. Ahmed, P. Kumar, A. Razzaq, N.A. Zaini, Y.F. Huang, M. Sherif, A. Sefelnasr, K.W. Chau, and A. El-Shafie. Wind speed prediction over Malaysia using various machine learning models: potential renewable energy source. Engineering Applications of Computational Fluid Mechanics 16(1): 1673-1689 (2022).
19. Y. Han, L. Mi, L. Shen, C. S. Cai, Y. Liu, K. Li, and G. Xu. A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting. Applied Energy 312: 118777 (2022).
20. E. Cadenas and W. Rivera. Short-term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks. Renewable Energy 35(1): 274-278 (2010).
21. A.M. Foley, P.G. Leahy, A. Marvuglia, and E.J. McKeogh. Current methods and advances in forecasting of wind power generation. Renewable Energy 37(1): 1-8 (2012).
22. M. Lydia, S.S. Kumar, A.I. Selvakumar, and E.P. Kumar. Linear and non-linear autoregressive models for short-term wind speed forecasting. Energy Conversion and Management 112: 115-124 (2016).
23. H. Liu, H.Q. Tian, and Y.F. Li. Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction. Applied Energy 98: 415-424 (2015).
24. W. Qamar, M. Hussain, M.B. Zaheer, J. Akram, N. Sadiq, and Z. Uddin. Prediction of sunspot numbers via Weibull distribution and deep learning. Astrophysics and Space Science 370(7): 68 (2025).
25. J. Merganič and H. Sterba. Characterisation of diameter distribution using the Weibull function: method of moments. European Journal of Forest Research 125(4): 427-439 (2006).
26. K. Mohammadi, O. Alavi, A. Mostafaeipour, N. Goudarzi, and M. Jalilvand. Assessing different parameters estimation methods of Weibull distribution to compute wind power density. Energy Conversion and Management 108: 322-335 (2016).
27. W.L. Hung and Y.C. Liu. Estimation of Weibull parameters using a fuzzy least-squares method. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 12(05): 701-711 (2004).
28. P. Malik, A. Gehlot, R. Singh, L. R. Gupta, and A.K. Thakur. A review on ANN based model for solar radiation and wind speed prediction with real-time data. Archives of Computational Methods in Engineering 29(5): 3183-3201 (2022).
29. A. Tahir, M. Ashraf, A. Razzak, S.M. Raza, and Z. Uddin. Temperature data of Hyderabad from the temperature of three neighboring cities using the ANN and the multiple regression methods. Kuwait Journal of Science 50(3A): 147-161 (2023).
30. W. Shepherd and L. Zhang (Eds.). Electricity Generation Using Wind Power. World Scientific (2017).
31. J.A. Carta, P. Ramirez, and C. Bueno. A joint probability density function of wind speed and direction for wind energy analysis. Energy Conversion and Management 49(6): 1309-1320 (2008).
32. M. A. Hussain, S. Abbas, M.R.K. Ansari, A. Zaffar, and B. Jan. Wind speed analysis of some coastal areas near Karachi. Proceedings of the Pakistan Academy of Sciences 51(1): 83-91 (2012).
33. M. Arashi, P. Nagar, and A. Bekker. Joint probabilistic modeling of wind speed and wind direction for wind energy analysis: A case study in humansdorp and noupoort. Sustainability 12(11): 4371 (2020).
34. Z. Wang and W. Liu. Wind energy potential assessment based on wind speed, its direction and power data. Scientific Reports 11(1): 16879 (2021).
35. A. Narain, S.K. Srivastava, and S.N. Singh. The impact of wind direction on wind farm power output calculation considering the wake effects of wind turbines. Wind Engineering 47(1): 74-85 (2023).
36. S.A. Mata, J.P. Martínez, J.B. Quesada, F.P. Larrañaga, N. Yadav, J.S. Chawla, V. Sivaram, and M.F. Howland. Modeling the effect of wind speed and direction shear on utility‐scale wind turbine power production. Wind Energy 27(9): 873-899 (2024).
37. M.A. Ghorbani, R. Khatibi, B. Hosseini, and M. Bilgili. Relative importance of parameters affecting wind speed prediction using artificial neural networks. Theoretical and Applied Climatology 114(1): 107-114 (2013).
38. M. Jamil and M. Zeeshan. A comparative analysis of ANN and chaotic approach-based wind speed prediction in India. Neural Computing and Applications 31(10): 6807-6819 (2019).
39. G. Li and J. Shi. On comparing three artificial neural networks for wind speed forecasting. Applied Energy 87(7): 2313-2320 (2010).
