Pregled bibliografske jedinice broj: 1143244
Countywide natural gas consumption forecast, a machine learning approach
Countywide natural gas consumption forecast, a machine learning approach // IEEE Explore - 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
Opatija, Hrvatska: Institute of Electrical and Electronics Engineers (IEEE), 2018. str. 1070-1073 doi:10.23919/mipro.2018.8400195 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), ostalo)
CROSBI ID: 1143244 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Countywide natural gas consumption forecast, a
machine learning approach
Autori
Sičanica, Zlatan ; Oklopčić, Zdravko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), ostalo
Izvornik
IEEE Explore - 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
/ - : Institute of Electrical and Electronics Engineers (IEEE), 2018, 1070-1073
Skup
41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2018)
Mjesto i datum
Opatija, Hrvatska, 21.05.2018. - 25.05.2018
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Natural gas ; forecasting ; regression ; machine learning ; optimization ; intelligent systems ; time series
Sažetak
This paper proposes several machine learning models for gas consumption forecast. The consumption data used is for a county in Croatia, and the considered models are decision trees, linear regressors, support vector regression, and neural networks. Most of the models show promising results when compared to similar research. The criterion used to identify the forecast quality is the root of the mean squared error, error being the forecast difference from the expected value. The findings presented in this paper can be used to better understand the way natural gas is consumed in the county and to create a more sophisticated regressor in the future.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
