Ensemble of various neural networks for prediction of heating energy consumption
Само за регистроване кориснике
2015
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
For prediction of heating energy consumption-of a university campus, various artificial neural networks are used: feed forward backpropagation neural network (FFNN), radial basis function network (RBFN) and adaptive neuro-fuzzy interference system (ANFIS). Actual measured data are used for training and testing the models. For each neural networks type, three models (using different number of input parameters) are analyzed. In order to improve prediction accuracy, ensemble of neural networks is examined. Three different combinations of output are analyzed. It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results.
Кључне речи:
Neural networks ensemble / Heating consumption predictionИзвор:
Energy and Buildings, 2015, 94, 189-199Издавач:
- Elsevier Science Sa, Lausanne
Финансирање / пројекти:
- Norwegian Programme in Higher Education, Research and Development in the Western Balkans [3
DOI: 10.1016/j.enbuild.2015.02.052
ISSN: 0378-7788
WoS: 000353845100016
Scopus: 2-s2.0-84925182116
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Jovanović, Radiša AU - Sretenović, Aleksandra AU - Živković, Branislav PY - 2015 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2198 AB - For prediction of heating energy consumption-of a university campus, various artificial neural networks are used: feed forward backpropagation neural network (FFNN), radial basis function network (RBFN) and adaptive neuro-fuzzy interference system (ANFIS). Actual measured data are used for training and testing the models. For each neural networks type, three models (using different number of input parameters) are analyzed. In order to improve prediction accuracy, ensemble of neural networks is examined. Three different combinations of output are analyzed. It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results. PB - Elsevier Science Sa, Lausanne T2 - Energy and Buildings T1 - Ensemble of various neural networks for prediction of heating energy consumption EP - 199 SP - 189 VL - 94 DO - 10.1016/j.enbuild.2015.02.052 ER -
@article{ author = "Jovanović, Radiša and Sretenović, Aleksandra and Živković, Branislav", year = "2015", abstract = "For prediction of heating energy consumption-of a university campus, various artificial neural networks are used: feed forward backpropagation neural network (FFNN), radial basis function network (RBFN) and adaptive neuro-fuzzy interference system (ANFIS). Actual measured data are used for training and testing the models. For each neural networks type, three models (using different number of input parameters) are analyzed. In order to improve prediction accuracy, ensemble of neural networks is examined. Three different combinations of output are analyzed. It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results.", publisher = "Elsevier Science Sa, Lausanne", journal = "Energy and Buildings", title = "Ensemble of various neural networks for prediction of heating energy consumption", pages = "199-189", volume = "94", doi = "10.1016/j.enbuild.2015.02.052" }
Jovanović, R., Sretenović, A.,& Živković, B.. (2015). Ensemble of various neural networks for prediction of heating energy consumption. in Energy and Buildings Elsevier Science Sa, Lausanne., 94, 189-199. https://doi.org/10.1016/j.enbuild.2015.02.052
Jovanović R, Sretenović A, Živković B. Ensemble of various neural networks for prediction of heating energy consumption. in Energy and Buildings. 2015;94:189-199. doi:10.1016/j.enbuild.2015.02.052 .
Jovanović, Radiša, Sretenović, Aleksandra, Živković, Branislav, "Ensemble of various neural networks for prediction of heating energy consumption" in Energy and Buildings, 94 (2015):189-199, https://doi.org/10.1016/j.enbuild.2015.02.052 . .