Machine Learning Algorithms for Vertical Wind Speed Data Extrapolation: Comparison and Performance Using Mesoscale and Measured Site Data
Abstract
:1. Introduction
1.1. Motivation and Incitement
1.2. Literature Review
1.3. Major Contributions and Organization
2. Theory and Methods
2.1. Considered ML Approaches
- Regression: Linear, Ridge, Lasso, and Elastic.
- Decision-making: Decision Trees (DT).
- Support vector machines: Support Vector Regression (SVR).
- Ensemble methods: Random Forest (RF).
2.2. Training Data Sources
2.3. Scenarios
- Scenario A: only mesoscale data is available to extrapolate the wind speed at 102 height.
- Scenario B: only observed data is available to extrapolate the wind speed at 102 height.
- Scenario C: observed, and mesoscale data are available to extrapolated wind speed at 102 height.
2.4. Assessment
- Mean Absolute Error (MAE);
- Mean Squared Error (MSE);
- Root Mean Squared Error (RMSE);
- Coefficient of determination ().
3. Results
3.1. Scenario A: Extrapolate Wind Speed Using Mesoscale Data from Newa
3.2. Scenario B: Extrapolate Wind Speeds Using Data from a Met Mast
3.3. Scenario C: Extrapolate Wind Speeds Using Data from a Met Mast and Mesoscale from the Newa
4. Discussion
4.1. Scenario A: Extrapolate Wind Speed Using Mesoscale Data from Newa
4.2. Scenario B: Extrapolate Wind Speeds Using Data from a Met Mast
4.3. Scenario C: Extrapolate Wind Speeds Using Data from a Met Mast and Mesoscale from the NEWA
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
ANN | Artificial Neural Network |
CRISP-DM | Cross Industrial Standard Process For Data Mining |
CV | Cross-Validation |
DNN | Deep Neural Network |
DT | Decision Trees |
LR | Linear Regression |
RG | Ridge Regression |
MAE | Mean Absolute Error |
MAPE | Mean Absolute Percent Error |
ML | Machine Learning |
MSE | Mean Square Error |
NaN | Not a Number Value |
NEWA | New European Wind Atlas |
OLS | Ordinary Least Squares |
PBLH | Planetary Boundary Layer Height |
Probability Density Function | |
RF | Random Forest |
RMSE | Root Mean Square Error |
SVM | Support Vector Machine |
WPD | Wind Power Density |
WRF | Weather Research Forecasting model |
WS | Wind Speed |
Appendix A. Ml Models Configuration
Appendix B. Performance Metrics
References
- International Renewable Energy Agency. Capacity Statistics 2019; Technical Report; IRENA: Abu Dhabi, United Arab Emirates, 2020. [Google Scholar]
- International Renewable Energy Agency. Future of Wind 2019; Technical Report; IRENA: Abu Dhabi, United Arab Emirates, 2020. [Google Scholar]
- Roeth, J. Wind Resource Assessment Handbook; AWS Truepower: New York, NY, USA, 2010. [Google Scholar]
- Gasch, R.; Twele, J. (Eds.) Wind Power Plants: Fundamentals, Design, Construction and Operation; Springer: Berlin/Heidelberg, Germany, 2012. [Google Scholar] [CrossRef]
- Valsaraj, P.; Drisya, G.V.; Kumar, K.S. A Novel Approach for the Extrapolation of Wind Speed Time Series to Higher Altitude Using Machine Learning Model. In Proceedings of the 2018 International CET Conference on Control, Communication, and Computing (IC4), Thiruvananthapuram, India, 5–7 July 2018; pp. 112–115. [Google Scholar] [CrossRef]
- Mohandes, M.A.; Rehman, S. Wind Speed Extrapolation Using Machine Learning Methods and LiDAR Measurements. IEEE Access 2018, 6, 77634–77642. [Google Scholar] [CrossRef]
- Europe Union. The New European Wind Atlas (NEWA); Geoscientific Model Development: Munich, Germany, 2020. [Google Scholar]
- Manwell, J.F. Wind Energy Explained: Theory, Design and Application; Wiley: Hoboken, NJ, USA, 2009. [Google Scholar]
- Eyecioglu, O.; Hangun, B.; Kayisli, K.; Yesilbudak, M. Performance comparison of different machine learning algorithms on the prediction of wind turbine power generation. In Proceedings of the 8th International Conference on Renewable Energy Research and Applications, ICRERA 2019, Brasov, Romania, 3–6 November 2019; pp. 922–926. [Google Scholar] [CrossRef]
- Malakhov, A.; Goncharov, F. Testing proaches for wind plants power output. In Proceedings of the 2019 International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), Moscow, Russia, 14–15 March 2019. [Google Scholar] [CrossRef]
- Liu, Y.; Zhang, H. An Empirical Study on Machine Learning Models for Wind Power Predictions. In Proceedings of the 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), Anaheim, CA, USA, 18–20 December 2017; pp. 758–763. [Google Scholar] [CrossRef]
- Ji, G.R.; Han, P.; Zhai, Y.J. Wind speed forecasting based on support vector machine with forecasting error estimation. In Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007, Hong Kong, China, 19–22 August 2007; Volume 5, pp. 2735–2739. [Google Scholar] [CrossRef]
- Brahimi, T. Using artificial intelligence to predict wind speed for energy application in Saudi Arabia. Energies 2019, 12, 4669. [Google Scholar] [CrossRef] [Green Version]
- Liu, Y.; Wang, J.; Collett, I.; Morton, Y.J. A Machine Learning Framework for Real Data Gnss-R Wind Speed Retrieval. In Proceedings of the IGARSS 2019—2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 28 July–2 August 2019; pp. 8707–8710. [Google Scholar] [CrossRef]
- Ali, M.E.K.; Hassan, M.Z.; Ali, A.B.; Kumar, J. Prediction of Wind Speed Using Real Data: An Analysis of Statistical Machine Learning Techniques. In Proceedings of the 2017 4th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2017, Mana Island, Fiji, 11–13 December 2017; pp. 259–264. [Google Scholar] [CrossRef]
- Ak, R.; Fink, O.; Zio, E. Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction. IEEE Trans. Neural Netw. Learn. Syst. 2016, 27, 1734–1747. [Google Scholar] [CrossRef] [PubMed]
- Albrecht, C.; Klesitz, M. Long-term correlation of wind measurements using neural networks: A new method for post-processing short-time measurement data. In Proceedings of the European Wind Energy Conference and Exhibition 2007, EWEC 2007, Milan, Italy, 7–10 May 2007; Volume 2, pp. 755–762. [Google Scholar]
- Cheggaga, N.; Ettoumi, F.Y. A Neural Network Solution for Extrapolation of Wind Speeds at Heights Ranging for Improving the Estimation of Wind Producible. Wind. Eng. 2011, 35, 33–53. [Google Scholar] [CrossRef]
- Türkan, Y.S.; Yumurtacı Aydoğmuş, H.; Erdal, H. The prediction of the wind speed at different heights by machine learning methods. Int. J. Optim. Control. Theor. Appl. 2016, 6, 179. [Google Scholar] [CrossRef]
- Cheggaga, N. A new artificial neural network–power law model for vertical wind speed extrapolation for improving wind resource assessment. Wind. Eng. 2018, 42, 510–522. [Google Scholar] [CrossRef]
- Vassallo, D.; Krishnamurthy, R.; Fernando, H.J.S. Decreasing wind speed extrapolation error via domain-specific feature extraction and selection. Wind. Energy Sci. 2020, 5, 959–975. [Google Scholar] [CrossRef]
- Bodini, N.; Optis, M. How accurate is a machine learning-based wind speed extrapolation under a round-robin approach? J. Phys. Conf. Ser. 2020, 1618, 062037. [Google Scholar] [CrossRef]
- Adli, F.; Cheggaga, N.; Farouk, H. Vertical wind speed extrapolation: Modelling using a response surface methodology (RSM) based on unconventional designs. Wind. Eng. 2022, 35, 33–53. [Google Scholar] [CrossRef]
- Emeksiz, C. Multi-gen genetic programming based improved innovative model for extrapolation of wind data at high altitudes, case study: Turkey. Comput. Electr. Eng. 2022, 100, 107966. [Google Scholar] [CrossRef]
- Shi, T.; He, G.; Mu, Y. Random Forest Algorithm Based on Genetic Algorithm Optimization for Property-Related Crime Prediction. In Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019), Qingdao, China, 27–29 March 2019; Atlantis Press: Amsterdam, The Netherlands, 2019; pp. 526–531. [Google Scholar] [CrossRef] [Green Version]
- Farooq, F.; Nasir Amin, M.; Khan, K.; Rehan Sadiq, M.; Faisal Javed, M.; Aslam, F.; Alyousef, R. A Comparative Study of Random Forest and Genetic Engineering Programming for the Prediction of Compressive Strength of High Strength Concrete (HSC). Appl. Sci. 2020, 10, 7330. [Google Scholar] [CrossRef]
- Feng, J. Artificial Intelligence for Wind Energy. In A State of the Art Report 978-87-93549-48-7; DTU Wind Energy: Lyngby, Denmark, 2019. [Google Scholar]
- Chapman, P.; Clinton, J.; Kerber, R.Y.; Shearer, C.; Khabaza, T. CRISP-DM 1.0. Step-by-Step Data Mining Guide; SPSS Inc.: Chicago, IL, USA, 2000. [Google Scholar]
- Subasi, A. Practical Machine Learning for Data Analysis Using Python; Elsevier: Amsterdam, The Netherlands, 2020. [Google Scholar] [CrossRef]
- Baquero, L. Extraction of Section 2.5 from the Thesis Book: Theory about Machine Learning Used in This Research; ResearchGate: Berlin, Germany, 2022; Volume 1, pp. 25–36. [Google Scholar]
- Zaharia, M.; Xin, R.S.; Wendell, P.; Das, T.; Armbrust, M.; Dave, A.; Meng, X.; Rosen, J.; Venkataraman, S.; Franklin, M.J.; et al. Apache spark: A unified engine for big data processing. Commun. ACM 2016, 59, 56–65. [Google Scholar] [CrossRef]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Seabold, S.; Perktold, J. Statsmodels: Econometric and statistical modeling with python. In Proceedings of the 9th Python in Science Conference, Austin, TX, USA, 28 June–3 July 2010. [Google Scholar]
- McKinney, W. Data structures for statistical computing in python. In Proceedings of the 9th Python in Science Conference, Austin, TX, USA, 28 June–3 July 2010; Volume 445, pp. 51–56. [Google Scholar]
- Hahmann, A.N.; Sile, T.; Witha, B.; Davis, N.N.; Dörenkämper, M.; Ezber, Y.; García-Bustamante, E.; González Rouco, J.F.; Navarro, J.; Olsen, B.T.; et al. The Making of the New European Wind Atlas, Part 1: Model Sensitivity; Technical Report; Model Sensitivity; Geoscientific Model Development: Munich, Germany, 2020. [Google Scholar] [CrossRef] [Green Version]
- Camuffo, D. Microclimate for Cultural Heritage: Conservation, Restoration, and Maintenance of Indoor and Outdoor Monuments, 2nd ed.; Elsevier: Amsterdam, The Netherland; Boston, MA, USA, 2014. [Google Scholar]
- DNV GL. Framework for Assurance of Data Driven Algorithms and Models; DNV GL: Oslo, Norway, 2020. [Google Scholar]
Item | Variable Name | Units | Nomenclature |
---|---|---|---|
1 | Wind speed | WS | |
2 | Wind Direcction | WD | |
3 | Air Temperature | T | |
4 | Friction velocity | UST | |
5 | Shortwave direct normal radiation | SWDDNI | |
6 | Shortwave diffuse incident radiation | SWDDRI | |
7 | Inverse Obukhov length | RMOL | |
8 | Planetary boundary layer height | PBLH | |
9 | Surface pressure | PSFC | |
10 | Surface latent Heat Flux | LH | |
11 | Water vapour mixing ratio | QVAPOR | |
12 | Turbulent kinetic energy | TKE |
Model | MAE | MSE | RMSE | CV |
---|---|---|---|---|
Linear | 1.288161 | 2.907878 | 1.70525 | 0.626386 |
Ridge | 1.274707 | 2.86232 | 1.691839 | 0.627854 |
Lasso | 1.273021 | 2.853636 | 1.689271 | 0.62787 |
ElasticNet | 1.271784 | 2.846432 | 1.687137 | 0.627652 |
Desicion Tree | 1.565074 | 4.166773 | 2.041268 | 0.408519 |
SVR | 1.288161 | 2.907878 | 1.70525 | 0.626386 |
Random Forest | 1.269825 | 2.819217 | 1.679052 | 0.633857 |
Model | MAE | MSE | RMSE | CV |
---|---|---|---|---|
Linear | 0.259943 | 0.283292 | 0.532251 | 0.97642 |
Ridge | 0.259976 | 0.283458 | 0.532408 | 0.975386 |
Lasso | 0.25996 | 0.283632 | 0.532571 | 0.975386 |
ElasticNet | 0.259969 | 0.283562 | 0.532505 | 0.975386 |
D. Tree | 0.279097 | 0.304115 | 0.551466 | 0.970416 |
SVR | 0.24582 | 0.284564 | 0.533445 | 0.977656 |
Rnd. Forest | 0.236336 | 0.278178 | 0.527425 | 0.97876 |
Model | MAE | MSE | RMSE | CV |
---|---|---|---|---|
Linear | 0.256397 | 0.281716 | 0.530769 | 0.976455 |
Ridge | 0.255516 | 0.280674 | 0.529786 | 0.976485 |
Lasso | 0.256068 | 0.281552 | 0.530615 | 0.976416 |
ElasticNet | 0.259969 | 0.283562 | 0.532505 | 0.975386 |
D. Tree | 0.317277 | 0.3508 | 0.592284 | 0.963366 |
SVR | 0.245733 | 0.283928 | 0.532849 | 0.977686 |
Rnd. Forest | 0.240971 | 0.281742 | 0.530794 | 0.978178 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Baquero, L.; Torio, H.; Leask, P. Machine Learning Algorithms for Vertical Wind Speed Data Extrapolation: Comparison and Performance Using Mesoscale and Measured Site Data. Energies 2022, 15, 5518. https://doi.org/10.3390/en15155518
Baquero L, Torio H, Leask P. Machine Learning Algorithms for Vertical Wind Speed Data Extrapolation: Comparison and Performance Using Mesoscale and Measured Site Data. Energies. 2022; 15(15):5518. https://doi.org/10.3390/en15155518
Chicago/Turabian StyleBaquero, Luis, Herena Torio, and Paul Leask. 2022. "Machine Learning Algorithms for Vertical Wind Speed Data Extrapolation: Comparison and Performance Using Mesoscale and Measured Site Data" Energies 15, no. 15: 5518. https://doi.org/10.3390/en15155518