20.500.12556/DKUM-83743 Napovedovanje porabe pitne vode z metodami časovnih vrst in strojnega učenja diplomsko delo Drinking water usage forecasting using methods of time series and machine learning V diplomski nalogi se ukvarjamo z napovedovanjem porabe pitne vode. Naš glavni cilj je primerjava napovednih modelov SARIMA in nevronske mreže LSTM. Pri napovedovanju se osredotočimo na časovne vrste posameznih gospodinjstev ter časovne vrste vodovodnega omrežja, ki so vzorčene mesečno. Primerjavo napovednih modelov izvedemo na podlagi njihove srednje kvadratne napake pri prileganju na časovno vrsto in napovedovanju porabe pitne vode na testni množici. Rezultati pokažejo, da se najbolje obnese model ARIMA. In this thesis we focus on forecasting drinking water usage. Our main goal is to compare the ARIMA models and the LSTM neural network model. We focus on forecasting time series of individual households and time series of water supply network, which are sampled monthly. Comparison of forecasting models is performed on basis of their mean squared error when fitting the time series and predicting drinking water consumption on the test set. The results show that the ARIMA model performs best. časovne vrste napovedovanje ARIMA LSTM time series forecasting ARIMA LSTM true true false [S. Dodič] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2023-01-30 09:04:31 2023-02-13 11:10:27 2023-04-15 03:06:18 0000-00-00 00:00:00 2023 0 Maribor 0 Maribor 1 spletni vir (1 datoteka PDF (IX, 29 f.)) 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 519.2+004.85(043.2) 149147651 UN_Dodic_Sara_2023.pdf UN_Dodic_Sara_2023.pdf 1 4C3237DEF77BECC849880BFBD7021DEE 1f451472b8397c786132706a31801252bac4370aaaf2a5af3b6a3e8444ae58a1 7505a548-a076-11ed-abc4-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=165491 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0