Institutional Repository of Vilnius University
Trumpalaikis Lietuvos nacionalinio elektros energijos suvartojimo modelis /
Abstract
dc:descriptionThis thesis investigates the problem of D-1 national electricity consumption forecasting in Lithuania. The aim of the study is to evaluate the accuracy of different machine learning methods for short-term electricity consumption forecasting. Ridge regression, decision tree, random forest, gradient boosting regression trees, multilayer perceptron, and hybrid stacking regression models were applied in the research. The impact of principal component analysis and feature selection on forecasting accuracy was also analyzed. The study used Lithuanian electricity consumption and meteorological data from 2022–2024. The best forecasting results were achieved by the multilayer perceptron, gradient boosting regression trees and the hybrid model. Model results improved further after feature selection.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Dagilis, Andrius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308333062&prefLang=en_US