University of Twente Student Theses
LSTM Modelling for Energy Prediction in the Current Global Context
Veverita, Valeria (2023) LSTM Modelling for Energy Prediction in the Current Global Context.
|
PDF
640kB |
| Abstract: | February 2022 marks the beginning of the Russian-Ukrainian conflict which targeted the lives of people that are even outside of the conflict. The energy sector is one of the major targets of geo-political events. The enforcement of energy sanctions by the western world caused economical changes which impacted the social models when it comes to energy consumption and raises questions about energy security. The new changes in the energy sector require the reevaluation of energy prediction models and the inclusion of socio-economic factors when predicting energy consumption models. This research aims to identify the socio-economic effect on the energy consumption prediction for the Netherlands and the Republic of Moldova. Two predictive models, the Long-Short Term Memory (LSTM) and Seasonal Auto- Regressive Integrated Moving Average with eXogenous factors (SARIMAX) models, will be assessed and compared for the energy prediction in the context of the current geo-political events. The accuracy of the models will be reevaluated by taking into consideration socio-economic factors such as energy price, inflation rate, world context factor, and weather factors. The result indicate that the energy forecasting for the Republic of Moldova is more dependant on socio-economic factors compared to the Netherlands when using the LSTM predictive model. On the contrary, for the seasonal energy prediction both countries display dependency on the socio-economic and weather factors. |
| 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/96190 |
| 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