Πρόβλεψη ηλεκτρικής κατανάλωσης σε σύμπλεγμα εμπορικών κτιρίων με την χρήση μεθόδων χρονικής συνάθροισης

Φακίνος, Γεώργιος Ν.; Fakinos, Georgios N.

dc.contributor.author	Φακίνος, Γεώργιος Ν.	el
dc.contributor.author	Fakinos, Georgios N.	en
dc.date.accessioned	2016-09-09T09:12:45Z
dc.date.available	2016-09-09T09:12:45Z
dc.date.issued	2016-09-09
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/43452
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.12999
dc.rights	Default License
dc.subject	Ενέργεια	el
dc.subject	Μέθοδοι προβλέψεων	el
dc.subject	Χρονική συνάθροιση	el
dc.subject	Ιεραρχική συνάθροιση	el
dc.subject	Αξιολόγηση προβλέψεων	el
dc.title	Πρόβλεψη ηλεκτρικής κατανάλωσης σε σύμπλεγμα εμπορικών κτιρίων με την χρήση μεθόδων χρονικής συνάθροισης	el
heal.type	bachelorThesis
heal.classification	Ενέργεια	el
heal.classification	Προβλέψεις	el
heal.language	el
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2016-06-13
heal.abstract	Εξατάζεται η πρόβλεψη κατανάλωσης ηλεκτρικής ενέργειας σε σύμπλεγμα εμπορικών κτιρίων. Γίνεται ο συνδυασμός μεθόδων ιεραρχικής (top down, bottom up, optimal) και χρονικής (MAPA) συνάθροισης με σκοπό να εξακριβωθεί το κατά πόσο συμβάλουν στην βελτίωση της ακρίβειας και στην μείωση της προκατάληψης των προβλέψεων.	el
heal.abstract	This paper examines the prediction electricity consumption buildings using temporal aggregation methods, i.e. the transition of the original data into multiple lower frequencies produce estimates in each of them separately. The aim is to ascertain to what extent these methods can help to achieve more accurate and unbiased estimations, taking advantage of the extra information that is hidden in each frequency studied. The study was done in a bank building complex and because the data we have are organized per energy use as well as per individual buildings of the bank the reconciliation of individual predictions is required to produce predictions at the lower levels of hierarchy summed in these higher. That requires the use of hierarchical data aggregation methods hierarchical aggregation). So the aim of this is to fill the gap that exists in the literature regarding production forecasts by combining temporal and hierarchical aggregation methods. In what ways can this be done and what will be the impact on the forecasts features are some of the questions that will be answered in this paper. What does energy consumption mean, what is the need and the steps taken for the study and this reduction and its importance for today's societies. Then we analyze the forecast methods, time series models and their characteristics and the analysis is done before the forecasting process. Aggregation methods and error indicators, that are used for the evaluation of methods, are then in depth analyzed. Finally we describe the methodology used in the study and briefly analyze the programming environment RStudio, which was used to export the results. To test the effect of the methods concerning the efficiency and accuracy of the forecast, a case study in five buildings of a bank is executed.	en
heal.advisorName	Ασημακόπουλος, Βασίλειος	el
heal.advisorName	Σπηλιώτης, Ευάγγελος	el
heal.committeeMemberName	Ασημακόπουλος, Βασίλειος	el
heal.committeeMemberName	Ψαρράς, Ιωάννης	el
heal.committeeMemberName	Ασκούνης, Δημήτριος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Ηλεκτρικών Βιομηχανικών Διατάξεων και Συστημάτων Αποφάσεων	el
heal.academicPublisherID	ntua
heal.numberOfPages	94 σ.
heal.fullTextAvailability	true