Predicting Solar Irradiance Using Machine Learning Approaches: The Case of Duzce, Turkey
Abstract views: 43
/ 
PDF downloads: 31
Keywords:
Photovoltaic panels, Solar irradiance Prediction, Machine learning, Hybrid Gradient BoostingAbstract
This research focuses on predicting the solar irradiance received by a standard photovoltaic
panel in Duzce, Turkey, using various machine learning techniques. The methodologies evaluated include
Bagging Learning, Decision Tree Learning, Gradient Boosting Learning, LightGBM Learning, Random
Forest Learning, Ridge Regression Learning, and XGBoost Learning. Through a comprehensive
comparative analysis, a Hybrid Gradient Boosting Learning approach is proposed for enhanced accuracy.
The study utilizes an extensive dataset comprising meteorological and sensor data, including Temperature
(T), Dew Point (DP), Humidity (H), Wind Speed (W), Pressure (P), Precipitation (PP), Total Feed-in
Time (TFT), Total Operating Time (TOT), Total Energy Produced (TWO), Number of Grid Connections
(OGSC), Environment Temperature Value (ETV), Module Temperature Value (MTV), and Radiation
(RD). The dataset spans from 2019 to 2024, and the RD value is predicted based on the other variables.
Random search was employed for hyperparameter optimization of the machine learning algorithms, with
the data divided into training and testing sets with an 80%-20% split. Performance metrics such as Mean
Squared Error (MSE), Mean Absolute Error (MAE), R² (Coefficient of Determination), Explained
Variance Score (EVS), Median Absolute Error (MedAE), and Mean Absolute Percentage Error (MAPE)
were used to evaluate the models. The results indicate that XGBoost achieved the highest performance,
while the proposed Hybrid Gradient Boosting model showed significant improvement over traditional
Gradient Boosting. The performance evaluations of each method are detailed, with graphical
representations and histograms demonstrating the efficacy of the proposed hybrid approach.
Downloads
References
C. B. Oguz, E. Avci, and S. B. Ozturk, “Analysis of PV power plant performance considering combination of different MPPT algorithms, shading patterns and connection types,” Eng. Sci. Technol. an Int. J., vol. 48, p. 101559, Dec. 2023, doi: 10.1016/j.jestch.2023.101559.
Ö. Ayvazoğluyüksel and Ü. B. Filik, “Estimation methods of global solar radiation, cell temperature and solar power forecasting: A review and case study in Eskişehir,” Renew. Sustain. Energy Rev., vol. 91, pp. 639–653, Aug. 2018, doi: 10.1016/j.rser.2018.03.084.
A. P. Grantham, P. J. Pudney, L. A. Ward, M. Belusko, and J. W. Boland, “Generating synthetic five-minute solar irradiance values from hourly observations,” Sol. Energy, vol. 147, pp. 209–221, May 2017, doi: 10.1016/j.solener.2017.03.026.
H. Bouzgou and C. A. Gueymard, “Fast short-term global solar irradiance forecasting with wrapper mutual information,” Renew. Energy, vol. 133, pp. 1055–1065, Apr. 2019, doi: 10.1016/j.renene.2018.10.096.
M. Ajith and M. Martínez-Ramón, “Deep learning algorithms for very short term solar irradiance forecasting: A survey,” Renew. Sustain. Energy Rev., vol. 182, p. 113362, Aug. 2023, doi: 10.1016/j.rser.2023.113362.
B. K. Puah et al., “A regression unsupervised incremental learning algorithm for solar irradiance prediction,” Renew. Energy, vol. 164, pp. 908–925, Feb. 2021, doi: 10.1016/j.renene.2020.09.080.
M. Golam, R. Akter, J.-M. Lee, and D.-S. Kim, “A Long Short-Term Memory-Based Solar Irradiance Prediction Scheme Using Meteorological Data,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2022, doi: 10.1109/LGRS.2021.3107139.
J. Ramirez-Vergara, L. B. Bosman, W. D. Leon-Salas, and E. Wollega, “Ambient temperature and solar irradiance forecasting prediction horizon sensitivity analysis,” Mach. Learn. with Appl., vol. 6, p. 100128, Dec. 2021, doi: 10.1016/j.mlwa.2021.100128.
H. Wen, Y. Du, X. Chen, E. G. Lim, H. Wen, and K. Yan, “A regional solar forecasting approach using generative adversarial networks with solar irradiance maps,” Renew. Energy, vol. 216, p. 119043, Nov. 2023, doi: 10.1016/j.renene.2023.119043.
X. Hou, C. Ju, and B. Wang, “Prediction of solar irradiance using convolutional neural network and attention mechanism-based long short-term memory network based on similar day analysis and an attention mechanism,” Heliyon, vol. 9, no. 11, p. e21484, Nov. 2023, doi: 10.1016/j.heliyon.2023.e21484.
E. Elibol and O. Dikmen, “Long-term performance investigation of different solar panels in the West Black Sea Region,” Clean Technol. Environ. Policy, vol. 26, no. 3, pp. 875–899, Mar. 2024, doi: 10.1007/s10098-023-02658-1.
A. K. Uysal and S. Gunal, “The impact of preprocessing on text classification,” Inf. Process. Manag., vol. 50, no. 1, pp. 104–112, Jan. 2014, doi: 10.1016/j.ipm.2013.08.006.
P. Ferreira, D. C. Le, and N. Zincir-Heywood, “Exploring Feature Normalization and Temporal Information for Machine Learning Based Insider Threat Detection,” in 2019 15th International Conference on Network and Service Management (CNSM), IEEE, Oct. 2019, pp. 1–7. doi: 10.23919/CNSM46954.2019.9012708.
L. Han et al., “Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data,” Plant Methods, vol. 15, no. 1, p. 10, Dec. 2019, doi: 10.1186/s13007-019-0394-z.
V. Joshua, S. M. Priyadharson, and R. Kannadasan, “Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu,” Agronomy, vol. 11, no. 10, p. 2068, Oct. 2021, doi: 10.3390/agronomy11102068.
J. D. de Guia, R. S. Concepcion II, H. A. Calinao, R. R. Tobias, E. P. Dadios, and A. A. Bandala, “Solar Irradiance Prediction Based on Weather Patterns Using Bagging-Based Ensemble Learners with Principal Component Analysis,” in 2020 IEEE 8th R10 Humanitarian Technology Conference (R10-HTC), IEEE, Dec. 2020, pp. 1–6. doi: 10.1109/R10-HTC49770.2020.9356988.
