University of Twente Student Theses
Explainable non-recurrent models for load forecasting
Verheijen, N.N.D.P. (2025) Explainable non-recurrent models for load forecasting.
|
PDF
980kB |
| Abstract: | As the world shifts towards green alternatives and self-sufficiency when it comes to the consumption and production of energy, a dramatic shift is required in the structuring of the electricity grid. One of the ways this is being solved is by the implementation and continued improvement of smart grids. A way to improve the current smart grids even further is through machine learning models in forecasting the load on the energy grid. This research aims to compare various types of machine learning models, specifically looking at non-recurrent models. The comparison will be made through the use of the Root Mean Square Error(RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R2). Long Short-Term Memory (LSTM) will be compared to The Neural Basis Expansion Analysis with Exogenous (N-BEATSx) and a Temporal Fusion Transformer (TFT). This study aims to find the explain-ability and interpretability of non-recurrent models for load forecasting, using the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/105129 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page