SENSITIVITY ANALYSIS OF HYPERPARAMETER IN SOLAR ENERGY PREDICTION MODEL USING GRADIENT BOOSTING METHOD

Aska Ramadhan; Bertha Maya Sopha; Mohammad Kholid Ridwan

doi:10.22146/ajse.v9i1.78322

SENSITIVITY ANALYSIS OF HYPERPARAMETER IN SOLAR ENERGY PREDICTION MODEL USING GRADIENT BOOSTING METHOD

https://doi.org/10.22146/ajse.v9i1.78322

Aska Ramadhan^(1*), Bertha Maya Sopha⁽²⁾, Mohammad Kholid Ridwan⁽³⁾

(1) Gadjah Mada University
(2) Gadjah Mada University
(3) Gadjah Mada University
(*) Corresponding Author

Abstract

Solar energy prediction is one alternative to handling unpredicted conditions of weather and solar radiation intensity. It could be the most important factor in achieving stability in electricity generation using solar energy resources. In making predictions, the use of machine learning models has been carried out by various methods, and in this study, the method used for the algorithm model is gradient boosting. In the modeling process using gradient boosting, several hyperparameter settings are needed. Hyperparameters have an important role in producing stable predictive patterns and can avoid overfitting or underfitting conditions. In this study, the accuracy and speed of prediction of the machine learning model with the gradient boosting approach, namely XGBoost and LightGBM, were analyzed in relation to setting the hyperparameter learning rate and max depth of the model's prediction pattern. The dataset used spans 6 months at a data resolution rate of every 5 minutes and includes meteorological data at the location point of Energy Laboratory UKRIM Yogyakarta as well as the output value of PLTS power and temperature panels onsite. Setting the hyperparameter learning rate in the highest and lowest conditions generates accuracy values with a difference of 2% and about the same prediction speed. With nMAE values of 2.84% and 1.35% and nRMSE values of 6.11% and 3.68%, respectively, the higher learning rate results in lower error values for both models. The XGBoost model shown tendency for overfitting and slower prediction speeds with the highest max depth setting. The prediction speed is faster at the lowest max depth condition, but the XGBoost and LightGBM models both exhibit underfitting.

Keywords

Machine learning; Hyperparameter; Solar energy prediction; Gradient boosting

Full Text:

PDF

References

Ahmed Kutty, H., Masral, M. H., & Rajendran, P. (2015). Regression model to predict global solar irradiance in Malaysia. International Journal of Photoenergy, 2015(January). https://doi.org/10.1155/2015/347023 Barrera, J. M., Reina, A., Maté, A., & Trujillo, J. C. (2020). Solar energy prediction model based on artificial neural networks and open data. Sustainability (Switzerland), 12(17). https://doi.org/10.3390/SU12176915 Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17-Augu, 785–794. https://doi.org/10.1145/2939672.2939785 Choi, S., & Hur, J. (2020). An ensemble learner-based bagging model using past output data for photovoltaic forecasting. Energies, 13(6). https://doi.org/10.3390/en13061438 IESR. (2021). Indonesia’s Largest of Solar Farm: Key Opportunities and Challenges. Indonesia’s Largest of Solar Farm. Ikhsan, M. (2020). Peramalan Energi Photovoltaic Dengan Menggunakan Algoritma Naive Bayes Classifier dan K-Nearest Neighbors. Universitas Islam Indonesia. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 2017-Decem(Nips), 3147–3155. Kim, S. G., Jung, J. Y., & Sim, M. K. (2019). A two-step approach to solar power generation prediction based on weather data using machine learning. Sustainability (Switzerland), 11(5). https://doi.org/10.3390/SU11051501 Lai, J. P., Chang, Y. M., Chen, C. H., & Pai, P. F. (2020). A survey of machine learning models in renewable energy predictions. Applied Sciences (Switzerland), 10(17). https://doi.org/10.3390/app10175975 Li, B. (2020). Random Search Plus: A more effective random search for Random Search Plus: A more effective random search for machine learning hyperparameters optimization machine learning hyperparameters optimization. https://trace.tennessee.edu/utk_gradthes/5849 Martínez, C. F. (2018). Bachelor Degree Thesis - Machine Learning for Solar Energy Prediction. University of Gavle, May, 1–80. Microsoft Coorporation. (2022). lightgbm-readthedocs-io-en-latest. LightGBM Documentation. https://lightgbm.readthedocs.io/en/v3.3.2/ Reba, K., Bevc, J., Vásquez, A.-, & Jankovec, M. (2019). Photovoltaic Energy Production Forecasting using LightGBM. 55th International Conference on Microelectronics, Devices and Materials with the Workshop on Laser Systems and Photonics, 36–39. Voyant, C., Notton, G., Kalogirou, S., Nivet, M. L., Paoli, C., Motte, F., & Fouilloy, A. (2017). Machine learning methods for solar radiation forecasting: A review. Renewable Energy, 105, 569–582. https://doi.org/10.1016/j.renene.2016.12.095 Widodo, D. A., Iksan, N., Udayanti, E. D., & Djuniadi. (2021). Renewable energy power generation forecasting using deep learning method. IOP Conference Series: Earth and Environmental Science, 700(1). https://doi.org/10.1088/1755-1315/700/1/012026 XGBoost developers. (2022). xgboost-readthedocs-io-en-latest. XGBoost Documentation. https://xgboost.readthedocs.io/en/stable/ Zhou, Z., Lin, A., He, L., & Wang, L. (2022). Evaluation of Various Tree-Based Ensemble Models for Estimating Solar Energy Resource Potential in Different Climatic Zones of China. Energies, 15(9). https://doi.org/10.3390/en15093463

DOI: https://doi.org/10.22146/ajse.v9i1.78322