University of Twente Student Theses


Error Estimation for Output Prediction of Photovoltaic Systems

Horst, Reinier L.C. van der (2022) Error Estimation for Output Prediction of Photovoltaic Systems.

[img] PDF
Abstract:Predictions for the power output of renewable energy sources are not always accurate. Gaining insight in the error of predictions can help grid operators manage the power grid more efficiently. This is especially important now that common households produce their own energy though photovoltaic (PV) systems more frequently. Currently, the increase in the amount of energy generated through PV systems already leads to congestion and damage to the main energy grid. To counter this development, more anticipating control is required, which in turn requires more insight into future energy generation. In this research paper, the viability of an independent centralised model that estimates the error in the power output predictions made by a PV system is analysed. Multiple Linear Regression and XGBoost are trained on weather data in order to estimate the error of a PV prediction model. Machine Learning models prove to be a viable tool to provide insight into the reliability of output predictions, especially in classifying probable over-/under-estimations.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:02 science and culture in general, 43 environmental science, 50 technical science in general, 54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page