THERMAL SCIENCE

International Scientific Journal

Marina M. Milićević

,

Budimirka R. Marinović

MACHINE LEARNING METHODS IN FORECASTING SOLAR PHOTOVOLTAIC ENERGY PRODUCTION

ABSTRACT
Energy has an effective role in economic growth and development of societies. This paper is studying the impact of climate factors on performance of solar power plant using machine learning techniques for underlying relationship among factors that impact solar energy production and for forecasting monthly energy production. In this context this work provides two machine learning methods: ANN for forecasting energy production and decision tree useful in understanding the relationships in energy production data. Both structures have horizontal irradiation, sunlight duration, average monthly air temperature, average maximal air temperature, average minimal air temperature and average monthly wind speed as inputs parameters and the energy production as output. Results have shown that used machine learning models perform effectively, ANN predicted the energy production of the PV power plant with a correla-tion coefficient higher than 0.97. The results can help stakeholders in determining energy policy planning in order to overcome uncertainties associated with renewable energy resources.
KEYWORDS
solar energy, Аrtificial Neural Network, Decision Tree
PAPER SUBMITTED: 2023-04-02
PAPER REVISED: 2023-05-23
PAPER ACCEPTED: 2023-05-31
PUBLISHED ONLINE: 2023-07-16
DOI REFERENCE: https://doi.org/10.2298/TSCI230402150M
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2024, VOLUME 28, ISSUE Issue 1, PAGES [479 - 488]
REFERENCES
  1. Batić, I. M., et al., Impact of Air Temperature and Wind Speed on the Efficiency of a Photovoltaic Power Plant: An Experimental Analysis, Thermal Science, 27 (2023), 1A, pp. 299-310
  2. Khatib, T., et al., Solar Energy Prediction for Malaysia Using Artificial Neural Networks, International Journal of Photoenergy, 2012 (2012), ID419504
  3. Sedai, A., et al., Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production, Forecasting, 5 (2023), 1, pp. 256-284
  4. Elsheikh, A. H., et al., Modeling of Solar Energy Systems Using Artificial Neural Network: A Comprehensive Review, Solar Energy, 190 (2019), Mar., pp. 622-639
  5. Ramsami P., Oree V., A Hybrid Method for Forecasting the Energy Output of Photovoltaic Systems, Energy Conversion and Management, 95 (2015), May, pp. 406-413
  6. Dumitru, C.-D., et al., Solar Photovoltaic Energy Production Forecast Using Neural Networks, Procedia Technology, 22 (2016), 1, pp 808-815
  7. Shen, Y., et al., Impact of Solar Radiation Variation on the Optimal Tilted Angle for Fixed Grid-Connected PV Array - Case Study in Beijing, Global Energy Interconnection, 1 (2018), 4, pp. 460-466
  8. El Maghraoui, et al., Smart Energy Management: A Comparative Study of Energy Consumption Forecasting Algorithms for an Experimental Open-Pit Mine, Energies, 15 (2022), 13, 4659
  9. Sharma, N., et al., Assessing Waste Marble Powder Impact on Concrete Flexural Strength Using Gaussian Process, SVM, and ANFIS, Processes, 10 (2022), 12, 2745
  10. Makinde, A., et al., Prediction of Crude Oil Viscosity Using Feed-Forward Backpropagation Neural Network (FFBPNN), Petroleum and Coal, 54 (2012), 2, pp. 120-131
  11. Liyew, M., Melese, A., Machine Learning Techniques to Predict Daily Rainfall Amount, Journal of Big Data, 8 (2021), 153
  12. Mitchell, R., et al., An Artifcial Intelligence Approach, Springer, New York, USA, 2013
  13. Cunningham, P., Delany, S. J., k-Nearest Neighbor Classifiers, Multiple Classifier Systems, 34 (2013), 8, pp. 1-17
  14. Suthaharan, S., Support Vector Machine Learning Models and Algorithms for Big Data Classification, Springer, New York, USA, 2016, pp. 207-235
  15. Kassambara, A., Practical guide to cluster analysis in R: Unsupervised machine learning, vol. 1, Sthda, www.sthda.com, 2017
  16. Femila Roseline, J., et al., Neural Network Modelling for Prediction of Energy in Hybrid Renewable Energy Systems, Energy Reports, 8 (2022), Suppl. 8, pp. 999-1008
  17. Fadare, D. A., Modelling of Solar Energy Potential in Nigeria Using an Artificial Neural Network Model, Applied Energy, 86 (2009), 9, pp. 1410-1422
  18. Ahmad, M. R.,, Yacine, J. R., Predictive Modelling for Solar Thermal Energy Systems: A Comparison of Support Vector Regression, Random Forest, Extra Trees and Regression Trees, Journal of Cleaner Pro-duction, 203 (2018), Dec., pp. 810-821
  19. Sedai, A., et al., Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production, Forecasting, 5 (2023), 1, pp. 256-284
  20. Cobaner, M., et al., Prediction of Hydropower Energy Using ANN for the Feasibility of Hydropower Plant Installation to an Existing Irrigation Dam, Water Resources Management, An International Journal, 22 (2008), June, pp. 757-774
  21. Hamzacebi, C., et al., Forecasting of Turkey's Monthly Electricity Demand by Seasonal Artificial Neural Network, Neural Compute & Applic, 31 (2019), Aug., pp. 2217-2231
  22. Adil, M., et al., Effect of Number of Neurons and a Layers in an Artificial Neural Network for Generalized Concrete Mix Design, Neural Computing and Applliications, 34 (2020), Sept., pp. 8355-8363
  23. Jayalakshmi, T., Santhakumaran, A., Statistical Normalization and Back Propagation for Classifcation, International Journal of Computer Theory and Engineering, 3 (2011), 1, pp. 1793-8201
  24. Lopes, M. N. G., et al., Artificial Neural Networks Approaches for Predicting the Potential for Hydro-power Generation: a Case Study for Amazon Region, Journal of Intelligents and Fuzzy Systems, 36 (2019), 6, pp. 5757-5772
  25. Da, L., Kun, S., Random Forest Solar Power Forecast Based on Classification Optimization, Energy, 187 (2019), 115940
  26. Tsai, C. C., et al., Decision Tree-Based Classifier Combined with Neural-Based Predictor for Water-Stage Forecasts in a River Basin During Typhoons: A Case Study in Taiwan, Environmental Engeenering Scence, 29 (2012), 2, pp. 108-116
PDF VERSION [DOWNLOAD]
Machine learning methods in forecasting solar photovoltaic energy production

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence