SARIMA models for power evolution in photovoltaic systems
DOI:
https://doi.org/10.56294/saludcyt20251971Keywords:
Power, Generation systems, Photovoltaic, SARIMA models, Genetic algorithms, RStudioAbstract
Introduction.- The increasing use of renewable energy in power generation systems has highlighted the need for efficient schemes to predict model parameters. In particular, photovoltaic systems require accurate tools to model and forecast solar energy generation behavior. Objective.-To formulate SARIMA models with high accuracy in fitting, explanation, and prediction of energy yields in solar photovoltaic systems, specifically focused on the plant located at Plaza del Duque de Béjar, Spain. Method.- A fitting strategy based on genetic algorithms was adopted to accelerate the estimation of the SARIMA model using hourly solar photovoltaic generation data. The auto.arima package in RStudio was employed as a methodological tool, enabling automatic selection and optimization of the best model parameters. Results.- The selected model was SARIMA (5,0,0)(2,1,0)242424, characterized by a stationary stochastic process with a clear seasonal component. The model showed remarkable estimation accuracy, with low standard errors in the autoregressive coefficients. Additionally, the model residuals were well-adjusted, displaying independence and absence of serial autocorrelation. Conclusions.- The proposed model demonstrated excellent predictive performance, supported by training error metrics (ME (Mean Error)= -1.344268 and MASE (Mean Absolute Scaled Error)= 0.7048786). Its sound mathematical structure and strong fit make it a reliable tool for forecasting photovoltaic solar energy in systems with similar characteristics.
References
1. Sobri S, Koohi-Kamali S, Rahim NA. Solar photovoltaic generation forecasting methods: A review. Energy Convers Manag. 2018; 156:459–97. http://dx.doi.org/10.1016/j.enconman.2017.11.019
2. Dada M, Popoola P. Recent advances in solar photovoltaic materials and systems for energy storage applications: a review. Beni-Suef Univ J Basic Appl Sci. 2023;12(1). http://dx.doi.org/10.1186/s43088-023-00405-5
3. Kim E, Akhtar MS, Yang O-B. Designing solar power generation output forecasting methods using time series algorithms: Global warming affected weather conditions. SSRN Electron J. 2022; http://dx.doi.org/10.2139/ssrn.4170513
4. Husein M, Chung I-Y. Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learning approach. Energies [Internet]. 2019 [citado el 5 de enero de 2025];12(10):1856. Disponible en: https://www.mdpi.com/1996-1073/12/10/1856
5. Aliberti A, Fucini D, Bottaccioli L, Macii E, Acquaviva A, Patti E. Comparative analysis of neural networks techniques to forecast global horizontal irradiance. IEEE Access. 2021;9:122829–46. http://dx.doi.org/10.1109/access.2021.3110167
6. Atique S, Noureen S, Roy V, Subburaj V, Bayne S, Macfie J. Forecasting of total daily solar energy generation using ARIMA: A case study. En: 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC). IEEE; 2019. p. 0114–9.
7. Runge J, Zmeureanu R. Forecasting energy use in buildings using artificial neural networks: A review. Energies. 2019;12(17):3254. http://dx.doi.org/10.3390/en12173254
8. Li L, Han C. ASARIMA: An adaptive harvested power prediction model for solar energy harvesting sensor networks. Electronics (Basel). 2022;11(18):2934. http://dx.doi.org/10.3390/electronics11182934
9. Qing X, Niu Y. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy (Oxf). 2018;148:461–8. http://dx.doi.org/10.1016/j.energy.2018.01.177
10. Salman D, Direkoglu C, Kusaf M, Fahrioglu M. Hybrid deep learning models for time series forecasting of solar power. Neural Comput Appl. 2024;36(16):9095–112. http://dx.doi.org/10.1007/s00521-024-09558-5
11. Junhuathon N, Chayakulkheeree K. Comparative study of short-term photovoltaic power generation forecasting methods. En: 2021 International Conference on Power, Energy and Innovations (ICPEI). IEEE; 2021. p. 159–62.
12. Jiang Y, Zheng L, Ding X. Ultra-short-term prediction of photovoltaic output based on an LSTM-ARMA combined model driven by EEMD. J Renew Sustain Energy. 2021;13(4). http://dx.doi.org/10.1063/5.0056980
13. Aghmadi A, El Hani S, Mediouni H, Naseri N, El Issaoui F. Hybrid solar forecasting method based on empirical mode decomposition and Back Propagation Neural Network. E3S Web Conf. 2021;231:02001. http://dx.doi.org/10.1051/e3sconf/202123102001
14. Mughal SN, Sood YR, Jarial RK. Design and optimization of photovoltaic system with a week ahead power forecast using autoregressive artificial neural networks. Mater Today. 2022;52:834–41. http://dx.doi.org/10.1016/j.matpr.2021.10.223
15. Rogier JK, Mohamudally N. Forecasting photovoltaic power generation via an IoT network using nonlinear autoregressive neural network. Procedia Comput Sci. 2019;151:643–50. http://dx.doi.org/10.1016/j.procs.2019.04.086
16. Sultan Mohd MR, Johari J, Ruslan FA, Abdul Razak N, Ahmad S, Mohd Shah AS. Analysis on parameter effect for solar radiation prediction modeling using NNARX. En: 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS). IEEE; 2021. p. 69–74.
17. Boubaker S, Kamel S, Kolsi L, Kahouli O. Forecasting of one-day-ahead global horizontal irradiation using block-oriented models combined with a swarm intelligence approach. Nat Resour Res. 2021;30(1):1–26. http://dx.doi.org/10.1007/s11053-020-09761-w
18. Zou L, Munir MS, Kim K, Hong CS. Day-ahead energy sharing schedule for the P2P prosumer community using LSTM and swarm intelligence. En: 2020 International Conference on Information Networking (ICOIN). IEEE; 2020. p. 396–401.
19. Benti NE, Chaka MD, Semie AG. Forecasting renewable energy generation with machine learning and deep learning: Current advances and future prospects. Sustainability. 2023;15(9):7087. http://dx.doi.org/10.3390/su15097087
20. Basmadjian R, Shaafieyoun A, Julka S. Day-ahead forecasting of the percentage of renewables based on time-series statistical methods. Energies. 2021;14(21):7443. http://dx.doi.org/10.3390/en14217443
21. Natarajan VA, Karatampati P. Survey on renewable energy forecasting using different techniques. En: 2019 2nd International Conference on Power and Embedded Drive Control (ICPEDC). IEEE; 2019. p. 349–54.
22. Singh B, Pozo D. A guide to solar power forecasting using ARMA models. En: 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe). IEEE; 2019. p. 1–4.
23. Fara L, Diaconu A, Craciunescu D, Fara S. Forecasting of energy production for photovoltaic systems based on ARIMA and ANN advanced models. Int J Photoenergy. 2021;2021:1–19. http://dx.doi.org/10.1155/2021/6777488
24. Marikkar U, Hassan ASJ, Maithripala MS, Godaliyadda RI, Ekanayake PB, Ekanayake JB. Modified Auto Regressive technique for univariate time series prediction of solar irradiance [Internet]. arXiv [eess.SP]. 2020. Disponible en: http://arxiv.org/abs/2012.03215
25. Reikard G, Hansen C. Forecasting solar irradiance at short horizons: Frequency and time domain models. Renew Energy. 2019;135:1270–90. http://dx.doi.org/10.1016/j.renene.2018.08.081
26. Seyedmahmoudian M, Jamei E, Thirunavukkarasu G, Soon T, Mortimer M, Horan B, et al. Short-term forecasting of the output power of a building-integrated photovoltaic system using a metaheuristic approach. Energies. 2018;11(5):1260. http://dx.doi.org/10.3390/en11051260
27. Das UK, Tey KS, Seyedmahmoudian M, Mekhilef S, Idris MYI, Van Deventer W, et al. Forecasting of photovoltaic power generation and model optimization: A review. Renew Sustain Energy Rev. 2018;81:912–28. http://dx.doi.org/10.1016/j.rser.2017.08.017
28. European Commission. PVGIS-SARAH3: Photovoltaic Geographical Information System. Obtenido de EU Science Hub https://ec.europa.eu/jrc/en/pvgis. 2024 may.
29. Kushwaha V, Pindoriya NM. Very short-term solar PV generation forecast using SARIMA model: A case study. En: 2017 7th International Conference on Power Systems (ICPS). IEEE; 2017. p. 430–5.
30. Kushwaha V, Pindoriya NM. A SARIMA-RVFL hybrid model assisted by wavelet decomposition for very short-term solar PV power generation forecast. Renew Energy. 2019;140:124–39. http://dx.doi.org/10.1016/j.renene.2019.03.020
31. Rajagukguk RA, Ramadhan RAA, Lee H-J. A review on deep learning models for forecasting time series data of solar irradiance and photovoltaic power. Energies. 2020;13(24):6623. http://dx.doi.org/10.3390/en13246623
32. Zhang X, Wu X, Zhu G, Lu X, Wang K. A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runoff prediction. Water Sci Technol Water Supply. 2022;22(8):6959–77. http://dx.doi.org/10.2166/ws.2022.263
33. Moeeni H, Bonakdari H, Ebtehaj I. Monthly reservoir inflow forecasting using a new hybrid SARIMA genetic programming approach. J Earth Syst Sci. 2017;126(2). http://dx.doi.org/10.1007/s12040-017-0798-y
34. Fashae OA, Olusola AO, Ndubuisi I, Udomboso CG. Comparing ANN and ARIMA model in predicting the discharge of River Opeki from 2010 to 2020. River Res Appl. 2019;35(2):169–77. Disponible en: http://dx.doi.org/10.1002/rra.3391
35. Harrou F, Taghezouit B, Sun Y. Robust and flexible strategy for fault detection in grid-connected photovoltaic systems. Energy Convers Manag. 2019;180:1153–66. http://dx.doi.org/10.1016/j.enconman.2018.11.022
36. Taghezouit B, Harrou F, Larbes C, Sun Y, Semaoui S, Arab A, et al. Intelligent monitoring of photovoltaic systems via simplicial empirical models and performance loss rate evaluation under LabVIEW: A case study. Energies. 2022;15(21):7955. http://dx.doi.org/10.3390/en15217955
37. Yesildal F, Ozakin AN, Yakut K. Optimization of operational parameters for a photovoltaic panel cooled by spray cooling. Eng Sci Technol Int J. 2022;25(100983):100983. http://dx.doi.org/10.1016/j.jestch.2021.04.002
38. Belghiti H, Kandoussi K, Chellakhi A, Mchaouar Y, El Otmani R, Sadek EM. Performance optimization of photovoltaic system under real climatic conditions using a novel MPPT approach. Energy Sources Recovery Util Environ Eff. 2024;46(1):2474–92.
39. Kumar, M., & Kumar, Y. (2020). Solar radiation forecasting using SARIMA model for Patiala city, Punjab, India. Materials Today: Proceedings, 33, 3739–3744. https://doi.org/10.1016/j.matpr.2020.08.413
40. Yona, A., Senjyu, T., Saber, A. Y., Urasaki, N., & Funabashi, T. (2013). Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system. Energy, 30(11–12), 2191–2204. https://doi.org/10.1016/j.energy.2004.03.001
41. Benmouiza, K., & Cheknane, A. (2013). Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models. Energy Conversion and Management, 75, 561–569. https://doi.org/10.1016/j.enconman.2013.08.027
Published
Issue
Section
License
Copyright (c) 2025 Juan Espinoza, Christian Reyes, Diana Campaña, Elsa Basantes, Jesús Rodríguez, Sandra Chasiluisa (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
