Skip to main navigation menu Skip to main content Skip to site footer
Plant Science Today (PST)

Research Articles

Vol. 12 No. 3 (2025)

Daily solar power prediction using machine learning: A model wise comparative study

DOI
https://doi.org/10.14719/pst.8861
Submitted
14 April 2025
Published
13-06-2025 — Updated on 01-07-2025
Versions

Abstract

Solar energy produced by photovoltaic panels is a vital energy source that offers numerous benefits to both the environment and society. However, meteorological variables such as solar irradiation, weather patterns, precipitation and climate conditions present significant challenges to seamless energy integration into the power grid. Accurate forecasting is essential to maintain supply-demand balance, optimize energy storage and ensure grid stability. This study leverages machine learning (ML) techniques to predict solar power generation and address renewable energy integration challenges. Nine ML models were employed, including linear regression, auto
regressive integrated moving average (ARIMA), artificial neural network (ANN), support vector machines (SVM), random forest (RF), decision tree, gradient boosting machine (GBM), light gradient boosting (LGBM) and extreme gradient boosting (XGBM). Inputs such as irradiance, humidity, minimum temperature, maximum temperature and surface pressure were used to train these models. The model performances were evaluated using metrics like root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The results highlighted ANN as the most effective model, achieving an RMSE of 274.84 kWh, MAE of 245.93 kWh and a MAPE of 5.26 %. This research contributes to the existing literature by addressing the relatively unexplored application of multiple machine learning models for predicting energy output from photovoltaic systems. A key novelty of this study is its ability to achieve accurate solar power forecasts using a limited dataset from a newly installed solar power plant, unlike many existing studies that rely on large volumes of data. Additionally, it explores the solar power production potential of Namakkal district in Tamil Nadu, India-a region with limited prior research.

References

  1. 1. Hsu DD, O'Donoughue P, Fthenakis V, Heath GA, Kim HC, Sawyer P, et al. Life cycle greenhouse gas emissions of crystalline silicon photovoltaic electricity generation: Systematic review and harmonization. J Ind Ecol. 2012;16(s1). https://doi.org/10.1111/j.1530-9290.2011.00439.x
  2. 2. Tajjour S, Chandel SS, Chandel R, Thakur N. Power generation enhancement analysis of a 400 kWp grid-connected rooftop photovoltaic power plant in a hilly terrain of India. Energy Sustain Dev. 2023;77:101333. https://doi.org/10.1016/j.esd.2023.101333
  3. 3. Chandel SS, Gupta A, Chandel R, Tajjour S. Review of deep learning techniques for power generation prediction of industrial solar photovoltaic plants. Sol Compass. 2023;8:100061. https://doi.org/10.1016/j.solcom.2023.100061
  4. 4. Tajjour S, Chandel SS, Alotaibi MA, Malik H, García Márquez FP, Afthanorhan A. Short-term solar irradiance forecasting using deep learning techniques: A comprehensive case study. IEEE Access. 2023;11:119851–61.
  5. 5. Rafati A, Joorabian M, Mashhr E, Shaker HR. High dimensional very short-term solar power forecasting based on a data-driven heuristic method. Energy. 2021;219:119647. https://doi.org/10.1016/j.energy.2020.119647
  6. 6. du Plessis AA, Strauss JM, Rix AJ. Short-term solar power forecasting: Investigating the ability of deep learning models to capture low-level utility-scale photovoltaic system behaviour. Appl Energy. 2021;285:116395. https://doi.org/10.1016/j.apenergy.2020.116395
  7. 7. Son N, Jung M. Analysis of meteorological factor multivariate models for medium- and long-term photovoltaic solar power forecasting using long short-term memory. Appl Sci. 2021;11:1:316. https://doi.org/10.3390/app11010316
  8. 8. Al-Dahidi S, Madhiarasan M, Al-Ghussain L, Abubaker AM, Ahmad AD, Alrbai M, et al. Forecasting solar photovoltaic power production: A comprehensive review and innovative data-driven modeling framework. Energies. 2024;17:16:4145. https://doi.org/10.3390/en17164145
  9. 9. Pieri E, Kyprianou A, Phinikarides A, Makrides G, Georghiou GE. Forecasting degradation rates of different photovoltaic systems using robust principal component analysis and ARIMA. IET Renew Power Gener. 2017;11(10):1245–52. https://doi.org/10.1049/iet-rpg.2017.0090
  10. 10. Tajjour S, Chandel SS, Malik H, Alotaibi MA, Ustun TS. A novel metaheuristic approach for solar photovoltaic parameter extraction using manufacturer data. Photonics. 2022;9:11:858. https://doi.org/10.3390/photonics9110858
  11. 11. Wang F, Lu X, Mei S, Su Y, Zhen Z, Zou Z, et al. A satellite image data based ultra-short-term solar PV power forecasting method considering cloud information from neighboring plant. Energy. 2022;238:121946. https://doi.org/10.1016/j.energy.2021.121946
  12. 12. Pasion C, Wagner T, Koschnick C, Schuldt S, Williams J, Hallinan K. Machine learning modeling of horizontal photovoltaics using weather and location data. Energies. 2020;13(10):2570.
  13. 13. Oladapo BI, Olawumi MA, Omigbodun FT. Machine learning for optimising renewable energy and grid efficiency. Atmosphere. 2024;15:10:1250. https://doi.org/10.3390/atmos15101250
  14. 14. Chang R, Bai L, Hsu CH. Solar power generation prediction based on deep Learning. Sustain Energy Technol Assess. 2021;47:101354. https://doi.org/10.1016/j.seta.2021.101354
  15. 15. Suanpang P, Jamjuntr P. Machine learning models for solar power generation forecasting in microgrid application implications for smart cities. Sustainability. 2024;16:14:6087. https://doi.org/10.3390/su16146087
  16. 16. Ibrar M, Hassan MA, Shaukat K, Alam TM, Khurshid KS, Hameed IA, et al. A machine learning-based model for stability prediction of decentralized power grid linked with renewable energy resources. Wirel Commun Mob Comput. 2022;2022(1):2697303. https://doi.org/10.1155/2022/2697303
  17. 17. Yadav AK, Malik H, Chandel SS. ANN based prediction of daily global solar radiation for photovoltaics applications. In: 2015 Annual IEEE India Conference (INDICON). 2015. p.1–5.
  18. 18. Pereira S, Canhoto P, Salgado R, Costa MJ. Development of an ANN based corrective algorithm of the operational ECMWF global horizontal irradiation forecasts. Sol Energy. 2019;185:387-405. https://doi.org/10.1016/j.solener.2019.04.070
  19. 19. Gundu V, Simon SP. Short term solar power and temperature forecast using recurrent neural networks. Neural Process Lett. 2021;53(6):4407–18. https://doi.org/10.1007/s11063-021-10606-7
  20. 20. Long H, Zhang C, Geng R, Wu Z, Gu W. A combination interval prediction model based on biased convex cost function and auto-encoder in solar power prediction. IEEE Trans Sustain Energy. 2021;12(3):1561–70.
  21. 21. Yuan X, Liu S, Feng W, Dauphin G. Feature importance ranking of random forest-based end-to-end learning algorithm. Remote Sens. 2023;15(21):5203.
  22. 22. Hillmer SC, Tiao GC. An ARIMA-model-based approach to seasonal adjustment. J Am Stat Assoc. 1982;77(377):63-70. https://doi.org/10.1080/01621459.1982.10477767
  23. 23. Newbold P. ARIMA model building and the time series analysis approach to forecasting. J Forecast. 1983;2(1):23–35. https://doi.org/10.1002/for.3980020104
  24. 24. Sairamya NJ, Susmitha L, Thomas George S, Subathra MSP. Hybrid approach for classification of electroencephalographic signals using time-frequency images with wavelets and texture features. In: Hemanth DJ, Gupta D, Emilia Balas V, editors. Intelligent data analysis for biomedical applications. Academic Press; 2019. p.253-73. https://doi.org/10.1016/B978-0-12-815553-0.00013-6
  25. 25. Hamzaçebi C. Improving artificial neural networks' performance in seasonal time series forecasting. Spec Sect Genet Evol Comput. 2008;178(23):4550-59. https://doi.org/10.1016/j.ins.2008.07.024
  26. 26. Vandeginste BGM, Massart DL, Buydens LMC, De Jong S, Lewi PJ, Smeyers-Verbeke J. Artificial neural networks. In: Vandeginste BGM, Massart DL, Buydens LMC, De Jong S, Lewi PJ, Smeyers-Verbeke J, editors. Data handling in science and technology. Elsevier; 1998. p. 649-99. https://doi.org/10.1016/S0922-3487(98)80054-3
  27. 27. Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–97. https://doi.org/10.1007/BF00994018
  28. 28. Mohammadi K, Shamshirband S, Anisi MH, Alam KA, Petković D. Support vector regression based prediction of global solar radiation on a horizontal surface. Energy Convers Manag. 2015;91:433-41. https://doi.org/10.1016/j.enconman.2014.12.015
  29. 29. Setiawati P, Karno ASB, Hastomo W, Sestri E, Kasoni D, Arif D, et al. Predicting solar power generation: A machine learning approach for grid stability and efficiency. J Pilar Nusa Mandiri. 2025;21(1):34–43.
  30. 30. Aning S, Przybyła-Kasperek M. Comparative study of twoing and entropy criterion for decision tree classification of dispersed data. Knowl-Based Intell Inf Eng Syst Proc 26th Int Conf KES2022. 2022;207:2434-43. https://doi.org/10.1016/j.procs.2022.09.301
  31. 31. Safari A, Kheirandish Gharehbagh H, Nazari Heris M. DeepVELOX: INVELOX wind turbine intelligent power forecasting using hybrid GWO–GBR algorithm. Energies. 2023;16:19:6889. https://doi.org/10.3390/en16196889
  32. 32. Sauer J, Mariani VC, dos Santos Coelho L, Ribeiro MHDM, Rampazzo M. Extreme gradient boosting model based on improved Jaya optimizer applied to forecasting energy consumption in residential buildings. Evol Syst. 2022;13(4):577–88. https://doi.org/10.1007/s12530-021-09404-2
  33. 33. Fan GF, Zhang LZ, Yu M, Hong WC, Dong SQ. Applications of random forest in multivariable response surface for short-term load forecasting. Int J Electr Power Energy Syst. 2022;139:108073. https://doi.org/10.1016/j.ijepes.2022.108073

Downloads

Download data is not yet available.