Machine learning-driven wind energy mapping enhanced by natural neighbor interpolation

Abstract

In the present work, a prediction on the wind energy potential in Semarang City (Central Java Province, Indonesia) has been performed by leveraging a novel combination of machine learning and natural neighbor interpolation (NNI) methodology. This integrated approach uniquely combines the predictive power of machine learning to estimate wind speeds based on historical and spatial data, with the spatial mapping capabilities of NNI, which provides a more accurate and seamless visualization of wind speed distribution. This combination addresses challenges of data sparsity and variability, offering a more reliable and localized mapping approach than traditional methods. Additionally, air density is considered to calculate energy density, enabling a comprehensive evaluation of wind energy potential. The results show an average monthly wind speed of 5.23 m/s, ranging from 3.38 m/s to 7.39 m/s. Wind speeds between 7 m/s and 10 m/s are predicted to occur for up to 10 months annually, with an estimated energy density of 102.7 W/m². These findings underscore the feasibility of small-scale wind power generation in the study area and provide actionable insights for advancing renewable energy policies and implementations at the local level.

Keywords

• Wind energy
• Machine learning
• Natural neighbor interpolation

Thanks

We would like to express our sincere gratitude to everyone who contributed to the completion of this research. Special thanks go to our funding agencies, colleagues, and mentors for their invaluable support and guidance. Your contributions have been instrumental in the success of this study.

References

1. [1] Sadorsky, P. Wind energy for sustainable development: Driving factors and future outlook. Journal of Cleaner Production 2021; 289, DOI: 10.1016/j.jclepro.2020.125779.
2. [2] Darwish, H, H, Al-Quraan, A. Machine Learning Classification and Prediction of Wind Estimation Using Artificial Intelligence Techniques and Normal PDF. Sustainability 2023; 15: 1-29, DOI: 10.3390/su15043270.
3. [3] Saidur, R, Rahim, N, A, Islam, M, A. Environmental impact of wind energy. Renewable and Sustainable Energy Reviews 2011; 15: 2423-2430, DOI: 10.1016/j.rser.2011.02.024.
4. [4] Enevoldsen, P, Permien, F-H. Mapping the Wind Energy Potential of Sweden: A Sociotechnical Wind Atlas. Journal of Renewable Energy 2018; 2018: 1-11, DOI: 10.1155/2018/1650794.
5. [5] Global Wind Energy Council. Global Wind Report 2022. Brussels: Global Wind Energy Council, 2022.
6. [6] Hanifi, S, Liu, X, Lin, Z. A Critical Review of Wind Power Forecasting Methods—Past, Present and Future. Energies 2020; 13: 1-24, DOI: 10.3390/en13153764.
7. [7] Hopp, W, Spearman, M. Factory Physics. New York: Springer, 2014.
8. [8] Manero, J, Bejar, J, Cortes, U. Wind Energy Forecasting with Neural Networks: A Literature Review. Computacion y Sistemas 2018; 22: 1085–1098, DOI:10.13053/CyS-22-4-3081.

9. [9] Sacie, M, Santos, M, López, R. Use of State-of-Art Machine Learning Technologies for Forecasting Offshore Wind Speed, Wave and Misalignment to Improve Wind Turbine Performance. Journal of Marine Science and Engineering 2022; 10: 1-18, DOI: 10.3390/jmse10070938.
10. [10] Shin, H, Rüttgers, M, Lee, S. Neural Networks for Improving Wind Power Efficiency: A Review. Fluids 2022; 7: 1-16, DOI: 10.3390/fluids7120367.
11. [11] Zhang, J, Jiang, X, Chen, X. Wind Power Generation Prediction Based on LSTM. In: ICMAI 2019. Proceedings of the 2019 4th International Conference on Mathematics and Artificial Intelligence; 12-15 April 2019: Association for Computing Machinery, pp. 85–89, DOI: 10.1145/3325730.3325735.
12. [12] Demolli, H, Dokuz, A S, Ecemis, A. Wind power forecasting based on daily wind speed data using machine learning algorithms. Energy Conversion and Management 2019; 198, DOI: 10.1016/j.enconman.2019.111823.
13. [13] Purba, N P, Kelvin, J, Sandro, R. Suitable locations of Ocean Renewable Energy (ORE) in Indonesia Region - GIS approached. In: Conference and Exhibition Indonesia – New Renewable Energy and Energy Conservation (The 3rd Indo-EBTKE ConEx 2014); 13 March 2015: Elsevier Ltd, pp: 230-238, DOI: 10.1016/j.egypro.2015.01.035.
14. [14] Ministry of Energy and Mineral Resources of the Republic of Indonesia. Handbook of Energy & Economic Statistics of Indonesia. Jakarta: Ministry of Energy and Mineral Resources of the Republic of Indonesia, 2023.
15. [15] Younis, A, Elshiekh, H, Osama, D. Wind Speed Forecast for Sudan Using the Two-Parameter Weibull Distribution: The Case of Khartoum City. Wind 2023; 3: 213-231, DOI: 10.3390/wind3020013.
16. [16] Shao, Y, Wang, J, Zhang, H. An advanced weighted system based on swarm intelligence optimization for wind speed prediction. Applied Mathematical Modelling 2021; 100: 780–804, DOI: 10.1016/j.apm.2021.07.024.
17. [17] Wang, C, Zhang, S, Xiao, L. Wind speed forecasting based on multi-objective grey wolf optimisation algorithm, weighted information criterion, and wind energy conversion system: A case study in Eastern China. Energy Conversion and Management 2021; 243, DOI: 10.1016/j.enconman.2021.114402.
18. [18] Tarek, Z, Shams, M Y, Elshewey, A M. Wind Power Prediction Based on Machine Learning and Deep Learning Models. Computer, Materials & Continua 2023; 74: 715-732, DOI: 10.32604/cmc.2023.032533.
19. [19] Cheng, Z, Wang, J. A new combined model based on multi-objective salp swarm optimization for wind speed forecasting. Applied Soft Computing 2020; 92, DOI: 10.1016/j.asoc.2020.106294.
20. [20] Krechowicz, A, Krechowicz, M, Poczeta, K. Machine Learning Approaches to Predict Electricity Production from Renewable Energy Sources. Energies 2022; 15, DOI: 10.3390/en15239146.
21. [21] Yürek, Ö E, Birant, D, Yürek, İ. Wind Power Generation Prediction Using Machine Learning Algorithms. DEUFMD 2021; 23: 107–119, DOI: 10.21205/deufmd.2021236709.
22. [22] Buturache, A N, Stancu, S. Wind Energy Prediction Using Machine Learning. Low Carbon Economy 2021; 12: 1–21, DOI: 10.4236/lce.2021.121001.
23. [23] Alkesaiberi, A, Harrou, F, Sun, Y. Efficient Wind Power Prediction Using Machine Learning Methods: A Comparative Study. Energies 2022; 15, DOI: 10.3390/en15072327.
24. [24] Kılıç, B. “Determination of wind dissipation maps and wind energy potential in Burdur province of Turkey using geographic information system (GIS). Sustainable Energy Technologies and Assessments 2019; 36, DOI: 10.1016/j.seta.2019.100555.
25. [25] Zahedi, R, Ghorbani, M, Daneshgar, S. Potential measurement of Iran’s western regional wind energy using GIS. Journal of Cleaner Production 2022; 330, DOI: 10.1016/j.jclepro.2021.129883.
26. [26] Noorollahi, Y, Yousefi, H, Mohammadi, M. Multi-criteria decision support system for wind farm site selection using GIS. Sustainable Energy Technologies Assessments 2016; 13: 38-50, DOI: 10.1016/j.seta.2015.11.007.
27. [27] Feng, J, Feng, L, Wang, J. Evaluation of the onshore wind energy potential in mainland China—Based on GIS modeling and EROI analysis. Resource, Conservation and Recycling 2020: 152, DOI: 10.1016/j.resconrec.2019.104484.
28. [28] Assouline, D, Mohajeri, N, Mauree, D. Machine learning and geographic information systems for large-scale wind energy potential estimation in rural areas. In: Journal of Physics Conference Series, Volume 1343, CISBAT 2019; 4-6 September 2019: IOP Publishing Ltd, pp. 1-6, DOI: 10.1088/1742-6596/1343/1/012036.
29. [29] Sachit, M S, Shafri, H Z M, Abdullah, A F. Global Spatial Suitability Mapping of Wind and Solar Systems Using an Explainable AI-Based Approach. ISPRS International Journal of Geo-Information 2022; 11: 1-26, DOI: 10.3390/ijgi11080422.
30. [30] Grassi, S, Veronesi, F, Schenkel, R. Mapping of the global wind energy potential using open source GIS data. In: Proceedings of the 2nd International Conference on Energy and Environment: bringing together Engineering and Economics, Guimarães, Portugal; 18-19 June 2015: ICEE, pp. 1-6.
31. [31] Music, E, Halilovic, A, Jusufovic, A. Wind Direction and Speed Prediction using Machine Learning. In: Proceedings of the 10th Days of BHAAAS in B&H - The International Symposium on Computer Science - ISCSAt, Jahorina, Bosnia and Herzegovina; 21 June 2018: ISCS, pp.1-8.
32. [32] Peiris, A T, Jayasinghe, J, Rathnayake, U. Forecasting wind power generation using artificial neural network: ‘Pawan danawi’ - A case study from Sri Lanka. Journal of Electrical and Computer Engineering 2021; 2021: 1-10, DOI: 10.1155/2021/5577547.
33. [33] Liu, M-D, Ding, L, Bai, Y-L. Application of hybrid model based on empirical mode decomposition, novel recurrent neural networks and the ARIMA to wind speed prediction. Energy Conversation and Management 2021; 233, DOI: 10.1016/j.enconman.2021.113917.
34. [34] Cao, Q, Ewing, B T, Thompson, M A. Forecasting wind speed with recurrent neural networks. European Journal of Operational Research 2012; 221: 148-154, DOI: 10.1016/j.ejor.2012.02.042.
35. [35] Childs, C. Interpolating Surfaces in ArcGIS Spatial Analyst. California: ESRI Education Services, 2004.
36. [36] Sukumar, N, Moran, B, Semenov, A Y. Natural neighbour Galerkin methods. International Journal for Numerical Methods in Engineering 2001; 50: 1–27, DOI: 10.1002/1097-0207.
37. [37] Manwell, J F, McGowan, J G, Rogers, A L. Wind Energy Explained: Theory, Design and Application, 2nd Edition. Michigan University: Wiley, 2009.
38. [38] Mentis, D, Hermann, S, Howells, M. Assessing the technical wind energy potential in Africa a GIS-based approach. Renewable Energy 2015; 83: 110–125, DOI: 10.1016/j.renene.2015.03.072.