Show simple item record

dc.creatorAntanasijević, Davor
dc.creatorPocajt, Viktor
dc.creatorRistić, Mirjana
dc.creatorPerić-Grujić, Aleksandra
dc.date.accessioned2021-03-10T12:44:57Z
dc.date.available2021-03-10T12:44:57Z
dc.date.issued2015
dc.identifier.issn0360-5442
dc.identifier.urihttp://TechnoRep.tmf.bg.ac.rs/handle/123456789/2987
dc.description.abstractThis paper presents a new approach for the estimation of energy-related GHG (greenhouse gas) emissions at the national level that combines the simplicity of the concept of GHG intensity and the generalization capabilities of ANNs (artificial neural networks). The main objectives of this work includes the determination of the accuracy of a GRNN (general regression neural network) model applied for the prediction of EC (energy consumption) and GHG intensity of energy consumption, utilizing general country statistics as inputs, as well as analysis of the accuracy of energy-related GHG emissions obtained by multiplying the two aforementioned outputs. The models were developed using historical data from the period 2004-2012, for a set of 26 European countries (EU Members). The obtained results demonstrate that the GRNN GHG intensity model provides a more accurate prediction, with the MAPE (mean absolute percentage error) of 4.5%, than tested MLR (multiple linear regression) and second-order and third-order non-linear MPR (multiple polynomial regression) models. Also, the GRNN EC model has high accuracy (MAPE = 3.6%), and therefore both GRNN models and the proposed approach can be considered as suitable for the calculation of GHG emissions. The energy-related predicted GHG emissions were very similar to the actual GHG emissions of EU Members (MAPE = 6.4%).en
dc.publisherPergamon-Elsevier Science Ltd, Oxford
dc.relationinfo:eu-repo/grantAgreement/MESTD/Basic Research (BR or ON)/172007/RS//
dc.rightsrestrictedAccess
dc.sourceEnergy
dc.subjectArtificial neural networksen
dc.subjectGRNN (general regression neural network)en
dc.subjectMultiple linear regressionen
dc.subjectMultiple polynomial regressionen
dc.titleModeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networksen
dc.typearticle
dc.rights.licenseARR
dc.citation.epage824
dc.citation.other84: 816-824
dc.citation.rankaM21
dc.citation.spage816
dc.citation.volume84
dc.identifier.doi10.1016/j.energy.2015.03.060
dc.identifier.rcubconv_4732
dc.identifier.scopus2-s2.0-84928437188
dc.identifier.wos000355035900077
dc.type.versionpublishedVersion


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record