 Testing long-term energy policy targets by means of artificial neural networkBranka D. Gvozdenac Urošević and Damir J. Đozić Energy, 2021, vol. 227, issue C Abstract: The main problem in trying to predict a certain process is an impossibility to manage changes that can occur in the future. When it comes to the application of artificial neural networks, the prediction of a target is established on training and testing that is based on what has happened in the past. In this paper, the prediction of the behavior of the energy system is based on changes of relevant parameters but bearing in mind the intensity and the time when these changes occur. Carbon-dioxide emissions in the European Union energy system in the time interval from 1990 to 2050 are analyzed and the prediction interval is divided into three intervals in accordance with the plans specified in the Energy Roadmap 2050. The simulation has always been conducted for a full interval starting from 1990 and the result of the previous interval is used to predict the next one. The results show that the prediction with presented training and testing algorithm is very flexible and that the effects of possible changes of relevant parameters in the interval that is the subject matter of the prediction can be reliably determined. Keywords: Artificial neural networks; Energy policy; European Union; Carbon-dioxide emissions (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:227:y:2021:i:c:s0360544221007192 DOI: 10.1016/j.energy.2021.120470 Access Statistics for this article Energy is currently edited by Henrik Lund and Mark J. Kaiser More articles in Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.