Pregled bibliografske jedinice broj: 878419
Modelling the Impact of Installation of Heat Cost Allocators in DH Systems Using Machine Learning
Modelling the Impact of Installation of Heat Cost Allocators in DH Systems Using Machine Learning // Interklima 2017 / Dović, Damir ; Soldo, Vladimir ; Mudrinić, Saša (ur.).
Zagreb: Fakultet strojarstva i brodogradnje Sveučilišta u Zagrebu, 2017. str. 24-24 (predavanje, nije recenziran, sažetak, ostalo)
CROSBI ID: 878419 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Modelling the Impact of Installation of Heat Cost Allocators in DH Systems Using Machine Learning
Autori
Maljković, Danica ; Balen, Igor ; Dalbelo Bašić, Bojana
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo
Izvornik
Interklima 2017
/ Dović, Damir ; Soldo, Vladimir ; Mudrinić, Saša - Zagreb : Fakultet strojarstva i brodogradnje Sveučilišta u Zagrebu, 2017, 24-24
Skup
24. MEĐUNARODNI SIMPOZIJ O GRIJANJU, HLAĐENJU I KLIMATIZACIJI / 24th INTERNATIONAL SYMPOSIUM ON HEATING, REFRIGERATING AND AIR CONDITIONING
Mjesto i datum
Zagreb, Hrvatska, 06.04.2017
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Nije recenziran
Ključne riječi
district heating, heat cost allocator, energy efficiency, machine learning
Sažetak
In accordance with provisions of the EU Directive on Energy Efficiency, specifically Article 9, individual metering in district heating systems had to be introduced by the end of 2016 in all Member States, Croatia being one of these. The Directive allows installation of both heat metering devices and heat cost allocators. Heat consumption is dependent on a number of factors, such as heating degree days, building envelope characteristics, occupancy, existence of individual metering as a basis for change in user’s behaviour, etc. It is a complex system to model the exact influence of the change of one of the heat consumption factors on overall consumption. In previous research there have been a number of studies on building energy consumption modelling and the usual methods used are traditional multiple regression models, simulation methods and methods of artificial neural networks. In this paper algorithms of machine learning will be used to isolate the sole impact of installation of heat cost allocators on a single building in multifamily buildings connected to district heating systems. The analysis is based on the real consumption data from 3.600 households in 60 multifamily buildings in different cities in Croatia.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Energetski institut