Support vector machine for the prediction of heating energy use
2018
Autori
Sretenović, AleksandraJovanović, Radiša
Novaković, Vojislav M.
Nord, Nataša M.
Živković, Branislav
Članak u časopisu (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks.
Ključne reči:
support vector machine / heating use prediction / artificial intelligence modelsIzvor:
Thermal Science, 2018, 22, S1171-S1181Izdavač:
- Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd
Finansiranje / projekti:
- Norwegian Programme in Higher Education, Research and Development in the Western Balkans, Programme 3: Energy Sector (HERD Energy)
DOI: 10.2298/TSCI170526126S
ISSN: 0354-9836
WoS: 000450540300018
Scopus: 2-s2.0-85057111447
Kolekcije
Institucija/grupa
Mašinski fakultetTY - JOUR AU - Sretenović, Aleksandra AU - Jovanović, Radiša AU - Novaković, Vojislav M. AU - Nord, Nataša M. AU - Živković, Branislav PY - 2018 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2893 AB - Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks. PB - Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd T2 - Thermal Science T1 - Support vector machine for the prediction of heating energy use EP - S1181 SP - S1171 VL - 22 DO - 10.2298/TSCI170526126S ER -
@article{ author = "Sretenović, Aleksandra and Jovanović, Radiša and Novaković, Vojislav M. and Nord, Nataša M. and Živković, Branislav", year = "2018", abstract = "Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks.", publisher = "Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd", journal = "Thermal Science", title = "Support vector machine for the prediction of heating energy use", pages = "S1181-S1171", volume = "22", doi = "10.2298/TSCI170526126S" }
Sretenović, A., Jovanović, R., Novaković, V. M., Nord, N. M.,& Živković, B.. (2018). Support vector machine for the prediction of heating energy use. in Thermal Science Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd., 22, S1171-S1181. https://doi.org/10.2298/TSCI170526126S
Sretenović A, Jovanović R, Novaković VM, Nord NM, Živković B. Support vector machine for the prediction of heating energy use. in Thermal Science. 2018;22:S1171-S1181. doi:10.2298/TSCI170526126S .
Sretenović, Aleksandra, Jovanović, Radiša, Novaković, Vojislav M., Nord, Nataša M., Živković, Branislav, "Support vector machine for the prediction of heating energy use" in Thermal Science, 22 (2018):S1171-S1181, https://doi.org/10.2298/TSCI170526126S . .