A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast
K. Schulte, L. Engel, L. Quakernack, F. Liegmann, J. Haubrock, in: N. Holjevac, T. Baškarad, M. Zidar, I. Kuzle (Eds.), IEEE PES ISGT Europe 2024 Conference Book, 2024.
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag
| Englisch
Autor*in
Herausgeber*in
Holjevac, Ninoslav;
Baškarad, Tomislav ;
Zidar, Matija ;
Kuzle, Igor
Abstract
Model predicitive control (MPC) applications require accurate and reliable forecasts of local photovoltaic (PV) generation. This work presents a novel approach to optimize local PV power forecasts with little measurement data. Different machine learning (ML) methods are compared regarding accuracy for optimizing a day-ahead PV power forecast. With an nMAE of 4.90%, the k-nearest-neighbors (KNN) regression method shows the best results overall and is well below the nMAE of 6.31% compared to the initial forecast. The different ML methods have their advantages in different weather conditions. The optimization of the PV forecast is practicable, as only little measurement data of the PV power is required and the PV power forecast can be used directly in MPC applications.
Erscheinungsjahr
Titel des Konferenzbandes
IEEE PES ISGT Europe 2024 Conference book
Konferenz
2024 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE)
Konferenzort
Dubrovnik, Croatia
Konferenzdatum
2024-10-14 – 2024-10-17
ISBN
FH-PUB-ID
Zitieren
Schulte, Katrin ; Engel, Lars ; Quakernack, Lars ; Liegmann, Fynn ; Haubrock, Jens: A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast. In: Holjevac, N. ; Baškarad, T. ; Zidar, M. ; Kuzle, I. (Hrsg.): IEEE PES ISGT Europe 2024 Conference book, 2024
Schulte K, Engel L, Quakernack L, Liegmann F, Haubrock J. A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast. In: Holjevac N, Baškarad T, Zidar M, Kuzle I, eds. IEEE PES ISGT Europe 2024 Conference Book. ; 2024.
Schulte, K., Engel, L., Quakernack, L., Liegmann, F., & Haubrock, J. (2024). A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast. In N. Holjevac, T. Baškarad, M. Zidar, & I. Kuzle (Eds.), IEEE PES ISGT Europe 2024 Conference book. Dubrovnik, Croatia.
@inproceedings{Schulte_Engel_Quakernack_Liegmann_Haubrock_2024, title={A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast}, booktitle={IEEE PES ISGT Europe 2024 Conference book}, author={Schulte, Katrin and Engel, Lars and Quakernack, Lars and Liegmann, Fynn and Haubrock, Jens}, editor={Holjevac, Ninoslav and Baškarad, Tomislav and Zidar, Matija and Kuzle, Igor Editors}, year={2024} }
Schulte, Katrin, Lars Engel, Lars Quakernack, Fynn Liegmann, and Jens Haubrock. “A Comparison of Machine Learning Algorithms for the Optimization of a Day-Ahead Photovoltaic Power Forecast.” In IEEE PES ISGT Europe 2024 Conference Book, edited by Ninoslav Holjevac, Tomislav Baškarad, Matija Zidar, and Igor Kuzle, 2024.
K. Schulte, L. Engel, L. Quakernack, F. Liegmann, and J. Haubrock, “A comparison of machine learning algorithms for the optimization of a day-ahead photovoltaic power forecast,” in IEEE PES ISGT Europe 2024 Conference book, Dubrovnik, Croatia, 2024.
Schulte, Katrin, et al. “A Comparison of Machine Learning Algorithms for the Optimization of a Day-Ahead Photovoltaic Power Forecast.” IEEE PES ISGT Europe 2024 Conference Book, edited by Ninoslav Holjevac et al., 2024.