DOI: https://doi.org/10.61435/ijred.2025.60547

Evaluating and analyzing the performance of PV power output forecasting using different models of machine-learning techniques considering prediction accuracy

1Laboratoire de génie mécanique et matériaux, Université 20 aout 1955 Skikda, Bp26 route d’el Hadaik Skikda, Algeria

2Département d'informatique, Université 20 aout 1955 Skikda, Bp26 route d’el Hadaik Skikda, Algeria

3Department of Electrical Engineering, University of Cádiz, Escuela Politécnica Superior de Algeciras, Avda. Ramón Puyol, s/n, 11202 Algeciras (Cádiz), Spain

4 Thermochemical Power Group (TPG), University of Genoa, Genoa, Italy

5 Department of Electrical Engineering, Escuela Superior de ingeniería de Puerto real, Avda. de la Universidad de Cádiz, 10 / 15519 Puerto Real (Cádiz), Spain

View all affiliations
Received: 10 Aug 2024; Revised: 7 Nov 2024; Accepted: 10 Dec 2024; Available online: 23 Dec 2024; Published: 1 Jan 2025.
Editor(s): Soulayman Soulayman
Open Access Copyright (c) 2025 The Author(s). Published by Centre of Biomass and Renewable Energy (CBIORE)
Creative Commons License This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Citation Format:
Abstract
Solar energy as a clean, renewable, and sustainable energy source has considerable potential to meet global energy needs. However, the intermittent and uncertain character of the solar energy source makes the power balance management a very challenging task. To overcome these shortcomings, providing accurate information about future energy production enables better planning, scheduling, and ensures effective strategies to meet energy demands. The present paper aims to assess the performance of PV power output forecasting in PV systems using various machine learning models, such as artificial neural networks (ANN), linear regression (LR), random forests (RF), and Support Vector Machines (SVM). These learning algorithms are trained on two different datasets with different time steps: in the first one, a historical weather forecast with a one hour time step, and in the second one, a dataset of on-site measurements with a 5-minute time step. To provide a reliable estimation of prediction accuracy for different learning algorithms, a k-fold cross-validation (CV) is applied. Through a comparison analysis, an assessment of the accuracy of these algorithms based on various metrics such as RMSE, MAE, and MRE is performed, providing a detailed evaluation of their performance. Results obtained from this study demonstrate that the random forest algorithm (RF) outperformed other algorithms in predicting PV output, achieving the smallest prediction error, where the best values for RMSE, MRE, MAE, and R² for the weather dataset were 0.856 W, 0.256%, 0.364 W, and 0.99999, respectively, while thevalues for RMSE, MRE, MAE, and R² for the on-site measurements dataset were 8.525 W, 11.163%, 3.922 W, and 0.99922, respectively.
Fulltext View|Download
Keywords: Solar energy; Power production; Energy forecasting; Machine learning; Cross-validation; Accuracy of predictions

Article Metrics:

Article Info
Section: Original Research Article
Language : EN
Recent articles
Unveiling the interactive effect of green technology innovation, employment of disabilities and sustainable energy: A new insight into inclusive sustainability A numerical H Darrieus hydrokinetic turbine performance assessment with the application of openings in blade geometry Do green foreign direct investments promote environmental innovation in European countries? Using hydrogen as potential fuel for internal combustion engines: A comprehensive assessment More recent articles
Most cited articles
Comparison of single and double stage regenerative organic rankine cycle for medium grade heat source through energy and exergy estimation MPPT Schemes for PV System under Normal and Partial Shading Condition: A Review Thermal and Ash Characterization of Indonesian Bamboo and Its Potential for Solid Fuel and Waste Valorization Power Quality Improvement Wind Energy System Using Cascaded Multilevel Inverter On the Eddy Current Losses in Metallic Towers More cited articles
  1. Abuella, M. and Chowdhury, B. (2015) Solar power forecasting using artificial neural networks, in 2015 North American Power Symposium (NAPS), pp. 1–5. https://doi.org/10.1109/NAPS.2015.7335176
  2. Antonanzas, J., Osorio, N., Escobar, R., Urraca, R., Martinez-de-Pison, F.J. & Antonanzas-Torres, F. (2016) Review of photovoltaic power forecasting, Solar Energy, 136, 78–111. https://doi.org/10.1016/j.solener.2016.06.069
  3. Arutyunov, V. S. and Lisichkin, G. V (2017) Energy resources of the 21st century: problems and forecasts. Can renewable energy sources replace fossil fuels?, Russian Chemical Reviews, 86(8), 777–804. https://doi.org/10.1070/rcr4723
  4. Bergmeir, C. and Benítez, J. M. (2012) On the use of cross-validation for time series predictor evaluation, Information Sciences, 191, 192–213. https://doi.org/10.1016/j.ins.2011.12.028
  5. Botchkarev, A. (2018) Evaluating Performance of Regression Machine Learning Models Using Multiple Error Metrics in Azure Machine Learning Studio, SSRN Electronic Journal. https://doi.org/10.2139/ssrn.3177507
  6. Breiman, L. E. O. (2001) Random Forests, 45, pp. 5–32
  7. Chen, J., Xiao, G., Ferrari, M. L., Yang, T., Ni, M., & Cen, K. (2020) Dynamic simulation of a solar-hybrid microturbine system with experimental validation of main parts, Renewable Energy, 154, 187–200. https://doi.org/10.1016/j.renene.2019.11.022
  8. Chenni, R., Makhlouf, M., Kerbache, T., & Bouzid, A. (2007) A detailed modeling method for photovoltaic cells, Energy, 32(9), pp. 1724–1730. https://doi.org/10.1016/j.energy.2006.12.006
  9. Deng, A. (2023) Time series cross validation: A theoretical result and finite sample performance, Economics Letters, 233(January). https://doi.org/10.1016/j.econlet.2023.111369
  10. Dimd, B. D., Völler, S., Cali, U., & Midtgård, O.-M. (2022) A Review of Machine Learning-Based Photovoltaic Output Power Forecasting: Nordic Context, IEEE Access, 10, 26404–26425. https://doi.org/10.1109/ACCESS.2022.3156942
  11. Gandelli, A., Grimaccia, F., Leva, S., Mussetta, M., & Ogliari, E. (2014) Hybrid model analysis and validation for PV energy production forecasting, Proceedings of the International Joint Conference on Neural Networks, pp. 1957–1962. https://doi.org/10.1109/IJCNN.2014.6889786
  12. De Giorgi, M. G., Congedo, P. M. and Malvoni, M. (2014) Photovoltaic power forecasting using statistical methods: Impact of weather data, IET Science, Measurement and Technology, 8(3), 90–97. https://doi.org/10.1049/iet-smt.2013.0135
  13. Haykin, S. (2009) Neural Networks and Learning Machines. 3rd edn. Edited by M. J. Horton. Ontario: Pearson
  14. Henderson, J. and Sen, A. (2021) The Energy Transition: Key challenges for incumbent and new players in the global energy system, The Oxford Institute for Energy Studies. http://hdl.handle.net/10419/246577
  15. Hope, T. M. H. (2020) Linear regression, pp. 67–81. https://doi.org/10.1016/B978-0-12-815739-8.00004-3
  16. Hoppe, T. and van Bueren, E. (2015) Guest editorial: governing the challenges of climate change and energy transition in cities, Energy, Sustainability and Society, 5(1). https://doi.org/10.1186/s13705-015-0047-7
  17. IEA (2023) Tracking Clean Energy Progress 2023, IEA. Available at: https://www.iea.org/reports/tracking-clean-energy-progress-2023, (Accessed: 3 December 2023)
  18. Iheanetu, K. J. (2022) Solar Photovoltaic Power Forecasting: A Review, Sustainability (Switzerland), 14(24). https://doi.org/10.3390/su142417005
  19. Khadke, S., Ramasubramanian, B., Paul, P., Lawaniya, R., Dawn, S., Chakraborty, A., Mandal, B., Dalapati, G. K., Kumar, A., & Ramakrishna, S. (2023) Predicting Active Solar Power with Machine Learning and Weather Data, Materials Circular Economy, 5(1), 15. https://doi.org/10.1007/s42824-023-00087-5
  20. Leva, S., Dolara, A., Grimaccia, F., Mussetta, M., & Ogliari, E. (2017) Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power, Mathematics and Computers in Simulation, 131, 88–100. https://doi.org/10.1016/j.matcom.2015.05.010
  21. Li, P., Zhou, K. and Yang, S. (2018) Photovoltaic Power Forecasting: Models and Methods, in 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), pp. 1–6. https://doi.org/10.1109/EI2.2018.8582674
  22. Liu, W., Liu, C., Lin, Y., Ma, L., Xiong, F., & Li, J. (2018) Ultra-short-term forecast of photovoltaic output power under fog and haze weather, Energies, 11(3). https://doi.org/10.3390/en11030528
  23. McCormick, P. G. and Suehrcke, H. (2018) The effect of intermittent solar radiation on the performance of PV systems, Solar Energy, 171, pp. 667–674. https://doi.org/10.1016/j.solener.2018.06.043
  24. Mellit, A., Massi Pavan, A., Ogliari, E., Leva, S., & Lughi, V. (2020) Advanced methods for photovoltaic output power forecasting: A review, Applied Sciences (Switzerland), 10(2). https://doi.org/10.3390/app10020487
  25. Müller, K.R., Smola, A.J., Rätsch, G., Schölkopf, B., Kohlmorgen, J., Vapnik, V. (1997). Predicting time series with support vector machines. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020283
  26. Amer, H. N., Dahlan, N. Y., Azmi, A. M., Latip, M. F. A., Onn, M. S., & Tumian, A. (2023) Solar power prediction based on Artificial Neural Network guided by feature selection for Large-scale Solar Photovoltaic Plant, Energy Reports, 9, 262–266. https://doi.org/10.1016/j.egyr.2023.09.141
  27. Notton, G., Nivet, M.-L., Voyant, C., Paoli, C., Darras, C., Motte, F., & Fouilloy, A. (2018) Intermittent and stochastic character of renewable energy sources: Consequences, cost of intermittence and benefit of forecasting, Renewable and Sustainable Energy Reviews. 87, 96–105. https://doi.org/10.1016/j.rser.2018.02.007
  28. NREL (2023) NSRDB: National Solar Radiation Database. Available at: https://nsrdb.nrel.gov/data-viewer
  29. Ozer, D. J. (1985) Correlation and the Coefficient of Determination, Psychological Bulletin, 97(2), 307–315. https://doi.org/10.1037/0033-2909.97.2.307
  30. Qi, J., Du, J., Siniscalchi, S. M., Ma, X., & Lee, C.-H. (2020) On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression, IEEE Signal Processing Letters, 27, 1485–1489. https://doi.org/10.1109/LSP.2020.3016837
  31. Rana, M., Koprinska, I. and Agelidis, V. G. (2016) Univariate and multivariate methods for very short-term solar photovoltaic power forecasting, Energy Conversion and Management. 121, 380–390. https://doi.org/10.1016/j.enconman.2016.05.025
  32. Rodríguez, F., Fleetwood, A., Galarza, A., & Fontán, L. (2018) Predicting solar energy generation through artificial neural networks using weather forecasts for microgrid control, Renewable Energy, 126, 855–864. doi: https://doi.org/10.1016/j.renene.2018.03.070
  33. Setiawan, A., Koprinska, I. and Agelidis, V. G. (2009) Very short-term electricity load demand forecasting using support vector regression, in 2009 International Joint Conference on Neural Networks, pp. 2888–2894. https://doi.org/10.1109/IJCNN.2009.5179063
  34. TamizhMani, G., Ji, L., Tang, Y., & Petacci, L. (2003) Photovoltaic Module Thermal/Wind Performance : Long-Term Monitoring and Model Development For Energy Rating, NCPV and Solar Program Review Meeting, (May), 936–939
  35. Tarroja, B., Mueller, F. and Samuelsen, S. (2013) Solar power variability and spatial diversification: implications from an electric grid load balancing perspective, International Journal of Energy Research, 37(9), 1002–1016. https://doi.org/10.1002/er.2903
  36. Thissen, U., van Brakel, R., de Weijer, A. P., Melssen, W. J., & Buydens, L. M. C. (2003) Using support vector machines for time series prediction, Chemometrics and Intelligent Laboratory Systems, 69(1), 35–49. https://doi.org/10.1016/S0169-7439(03)00111-4
  37. Yin, J., Molini, A. and Porporato, A. (2020) Impacts of solar intermittency on future photovoltaic reliability, Nature Communications. Springer US, 11(1), pp. 1–9. https://doi.org/10.1038/s41467-020-18602-6
  38. Yona, A., Senjyu, T., Funabashi, T., & Kim, C.-H. (2013) Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction, IEEE Transactions on Sustainable Energy, 4(2), 527–533. https://doi.org/10.1109/TSTE.2013.2246591
  39. Zack, J. W. (2017) Wind and Solar Forecasting. USA: Springer. https://doi.org/10.1007/978-3-319-55581-2_4
  40. Zhou, Y., Zhou, N., Gong, L., & Jiang, M. (2020) Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine, Energy, 204, 117894. https://doi.org/10.1016/j.energy.2020.117894

Last update:

No citation recorded.

Last update: 2025-02-08 02:33:11

No citation recorded.