Application of аrtificial neural networks for prediction of heating energy consumption in university buildings
Апстракт
In this study, the main objective is to predict heating consumption using artificial neural networks with several input parameters. For training and testing, daily meteorological and heating consumption data for Norwegian University of Science and Technology - NTNU University campus Gløshaugen were used. In order to determine the optimal network architecture, various network architectures were designed and different training algorithms were used. Also, the number of neurons and hidden layers and activation functions in the hidden layer/output layer were changed. Training of the network was performed by using Levenberg–Marquardt feedforward backpropagation algorithms. For each network, different indices of the prediction accuracy were calculated and compared.
Кључне речи:
heating energy consumption / prediction / artificial neuron networkИзвор:
Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology”, 2014, 18, 1, 163-166Финансирање / пројекти:
- Norwegian Programme in Higher Education, Research and Development in the Western Balkans, Programme 3: Energy Sector (HERD Energy)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Jovanović, Radiša AU - Sretenović, Aleksandra AU - Živković, Branislav PY - 2014 UR - https://machinery.mas.bg.ac.rs/handle/123456789/5054 AB - In this study, the main objective is to predict heating consumption using artificial neural networks with several input parameters. For training and testing, daily meteorological and heating consumption data for Norwegian University of Science and Technology - NTNU University campus Gløshaugen were used. In order to determine the optimal network architecture, various network architectures were designed and different training algorithms were used. Also, the number of neurons and hidden layers and activation functions in the hidden layer/output layer were changed. Training of the network was performed by using Levenberg–Marquardt feedforward backpropagation algorithms. For each network, different indices of the prediction accuracy were calculated and compared. C3 - Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology” T1 - Application of аrtificial neural networks for prediction of heating energy consumption in university buildings EP - 166 IS - 1 SP - 163 VL - 18 UR - https://hdl.handle.net/21.15107/rcub_machinery_5054 ER -
@conference{ author = "Jovanović, Radiša and Sretenović, Aleksandra and Živković, Branislav", year = "2014", abstract = "In this study, the main objective is to predict heating consumption using artificial neural networks with several input parameters. For training and testing, daily meteorological and heating consumption data for Norwegian University of Science and Technology - NTNU University campus Gløshaugen were used. In order to determine the optimal network architecture, various network architectures were designed and different training algorithms were used. Also, the number of neurons and hidden layers and activation functions in the hidden layer/output layer were changed. Training of the network was performed by using Levenberg–Marquardt feedforward backpropagation algorithms. For each network, different indices of the prediction accuracy were calculated and compared.", journal = "Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology”", title = "Application of аrtificial neural networks for prediction of heating energy consumption in university buildings", pages = "166-163", number = "1", volume = "18", url = "https://hdl.handle.net/21.15107/rcub_machinery_5054" }
Jovanović, R., Sretenović, A.,& Živković, B.. (2014). Application of аrtificial neural networks for prediction of heating energy consumption in university buildings. in Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology”, 18(1), 163-166. https://hdl.handle.net/21.15107/rcub_machinery_5054
Jovanović R, Sretenović A, Živković B. Application of аrtificial neural networks for prediction of heating energy consumption in university buildings. in Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology”. 2014;18(1):163-166. https://hdl.handle.net/21.15107/rcub_machinery_5054 .
Jovanović, Radiša, Sretenović, Aleksandra, Živković, Branislav, "Application of аrtificial neural networks for prediction of heating energy consumption in university buildings" in Proceedings of the 18th International Research/Expert Conference “Trends in the Development of Machinery and associated Technology”, 18, no. 1 (2014):163-166, https://hdl.handle.net/21.15107/rcub_machinery_5054 .