XGBOOST ALGORITHM FOR ORECASTING ELECTRICITY CONSUMPTION OF GERMANY

Year 2023, Volume: 7 Issue: 1, 99 - 108, 30.06.2023

Abdullahı Abdu Ibrahım Khalıd Mohamed Abdullah Elzarıdı

https://doi.org/10.53600/ajesa.1321195

Abstract

Stability requires energy demand prediction. We train and test 24-hour German load forecasting models. ENTSO-E Transparency Platform data covered European energy generation, transmission, and consumption. It uses German load data instead of PJM data for the eastern US, adds holidays and lag features to the XGB model, and benchmarks with a linear model and a random forest. Grid search CV refines the final XGB model. National load forecasting RMSE is 1740MW, which is suitable for the gradient boosting model. H-24 and H-48 lag is the most important for this job. Weekends and holidays help, but less. Regional holidays, average temperatures, and lag characteristics could improve the model (beyond H-48).

Keywords

Consumption, Electricity, Forecasting, Regression, XGBoost.

References

• Centro Nacional de Despacho - ETESA. (2020). Home - Centro Nacional de Despacho - ETESA. Retrieved from https://www.cnd.com.pa/ (accessed Jan. 11, 2023).
• Centro Nacional de Despacho - ETESA. (2020). Metodologías de Detalle - Centro Nacional de Despacho - ETESA. Retrieved from https://cnd.com.pa/index.php/acerca/documentos/normas/981-metodologias-de-detalle-2 (accessed Jan. 11, 2023).
• Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Retrieved from Mar. 2016, doi: 10.1145/2939672.2939785
• Forecaster | Hitachi Energy. (2023). Retrieved from https://www.hitachienergy.com/products-and-solutions/energy-portfolio-management/trading-and-risk-management/forecaster (accessed Jan. 11, 2023).
• Madid, E. A., & Bosquez, L. V. (2017). Impacto de la entrada de la generación eólica y fotovoltaica en Panamá. I+D Tecnológico, 13(1), 71–82. Retrieved from https://revistas.utp.ac.pa/index.php/id-tecnologico/article/view/1440/html
• Morales-España, G., Latorre, J. M., & Ramos, A. (2013). Tight and compact MILP formulation of start-up and shut-down ramping in unit commitment. IEEE Transactions on Power Systems, 28(2), 1288–1296. doi: 10.1109/TPWRS.2012.2222938
• PSR | NCP — Short term operation programming. (2023). Retrieved from https://www.psr-inc.com/softwares-en/?current=p4034 (accessed Jan. 11, 2023).
• Wood, A. J., Wollenberg, B. F., & Sheblé, G. B. (2013). Power generation, operation, and control. John Wiley & Sons. Retrieved from https://books.google.com.tr/books?hl=en&lr=&id=JDVmAgAAQBAJ&oi=fnd&pg=PA17&ots=CSPViJj2h3&sig=5HS1-xR4-Wl2maC8Vth4iB4H_7I&redir_esc=y#v=onepage&q&f=false (accessed Jan. 11, 2023).