Predviđanje utroška energije uporabom vremenskih nizova

master's thesis

• Title (english): Prediction of energy consumption using time series models
• Author: Matija Ostrunić
• Mentor: Hrvoje Cajner (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2020-05-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Tema ovog rada je predviđanje utroška energije uporabom vremenskih nizova (serija). Vremenski niz ili serija jest slijed izmjerenih vrijednosti promatrane pojave realiziran u vremenskoj domeni tj. određenom vremenskom periodu. Cilj rada je izraditi predikcijski model pomoću kojeg će se moći predvidjeti buduća potrošnja energije, te iskoristiti tako generirano znanje za donošenje ispravnih odluka.
U prvom dijelu rada ukratko su opisani fundamentalni pojmovi vezani uz vremenske nizove, te sam proces nastanka predikcijskog modela temeljenog na vremenskom nizu. Nakon upoznavanja s vremenskim nizovima, dan je prikaz najčešće korištenih statističkih metoda za predviđanje budućih stanja vremenskih nizova. U nastavku rada precizno je definiran glavni cilj predviđanja. U glavnom dijelu rada analiziran je realni sustav i podaci dobiveni iz njega. Nakon analize podataka slijedi izrada i usporedba predikcijskih modela. Na kraju rada je iznesena usporedba dobivenih rezultata te su prezentirani zaključci.

Abstract (english)

The scope of this paper is prediction of energy consumption using time series. A time series is a sequence of measured values of an observed phenomenon realized in time domain. The aim of the paper is to create a model that can predict energy consumption and leverage generated knowledge.
The first part of the paper briefly describes the fundamental concepts related to time series and the process of creating a prediction model based on them. After introduction, the most commonly used statistical methods are presented. The following section precisely defines main objective of prediction. Afterwards, physical system and data obtained from it are analyzed. Data analysis is followed by the creation and comparison of prediction models. At the end of the paper, an analysis of the obtained results is presented. Ultimately, conclusions and learnings are shared.

• Keywords: vremenski niz; predviđanje; utrošak energije; ARIMA metoda; metoda eksponencijalnog zaglađivanja
• Keywords (english): time series; forecasting; energy consumption; ARIMA; exponential smoothing method
• Language: croatian
• URN:NBN: urn:nbn:hr:235:054216
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-05-07 10:21:44