dc.contributor.author | Hansen, Martin | |
dc.date.accessioned | 2017-09-18T07:21:20Z | |
dc.date.available | 2017-09-18T07:21:20Z | |
dc.date.issued | 2017 | |
dc.identifier.uri | http://hdl.handle.net/11250/2455008 | |
dc.description | Master's thesis Information- and communication technology IKT590 - University of Agder 2017 | nb_NO |
dc.description.abstract | Convolutional Neural Networks are overwhelmingly accurate when
attempting to predict numbers using the famous MNIST-dataset. In
this paper, we are attempting to transcend these results for time-
series forecasting, and compare them with several regression mod-
els. The Convolutional Neural Network model predicted the same
value through the entire time lapse in contrast with the other models,
while the Multi-Layer Perception through Machine Learning model
performed overall best. Temperature variables are directly related
to power consumption, but the weights from the power consumption
values from 1, 2, 3, etc hours before the forecasting revealed to be
dominating the temperature weights. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Universitetet i Agder ; University of Agder | nb_NO |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/deed.no | * |
dc.subject | IKT590 | nb_NO |
dc.title | Prediction of Electricity Usage Using Convolutional Neural Networks | nb_NO |
dc.type | Master thesis | nb_NO |
dc.subject.nsi | VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 | nb_NO |
dc.source.pagenumber | IX, 58 p. | nb_NO |