Pregled bibliografske jedinice broj: 1131801
Prediction of User-defined Room Temperature Setpoints by LSTM Neural Networks
Prediction of User-defined Room Temperature Setpoints by LSTM Neural Networks // Proceedings of the 23rd International Conference on Process Control (PC) / Paulen, R. ; Fikar, M. (ur.).
Vysoké Tatry: Institute of Electrical and Electronics Engineers (IEEE), 2021. str. 169-174 doi:10.1109/PC52310.2021.9447534 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1131801 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Prediction of User-defined Room Temperature
Setpoints by LSTM Neural Networks
Autori
Perić, Nikica ; Novak, Hrvoje ; Rukavina, Filip ; Lešić, Vinko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 23rd International Conference on Process Control (PC)
/ Paulen, R. ; Fikar, M. - Vysoké Tatry : Institute of Electrical and Electronics Engineers (IEEE), 2021, 169-174
ISBN
978-1-6654-4791-1
Skup
23rd International Conference on Process Control
Mjesto i datum
Vysoké Tatry, Slovačka, 01.06.2021. - 04.06.2021
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
user behavior modelling ; room temperature reference prediction ; deep learning ; LSTM ; neural networks
Sažetak
Buildings are one of the largest consumers of energy in the world and as such an opportunity for significant energy savings. Modelling of user behavior is a prerequisite for predicting the building energy consumption that offers a possibility to adapt the building operation to best suit the user requirements while achieving minimal energy consumption through room air conditioning. In this paper, a deep learning model for prediction of an individual room temperature setpoint provided by the user is presented. Model learning was conducted on the available dataset containing external weather and internal climate measurements. External weather conditions consist of air temperature, relative humidity and direct, diffuse and global solar irradiation. The internal conditions refer to four offices for which the air temperature, the mode of operation of the fan coil controller and the temperature setpoint are available. The model was built using a neural network with Long Short- Term Memory. The highest accuracy was achieved by the model in which the variables on the old setpoint, system working, day of the week and relative humidity were used. Presented results show high model accuracy, applicable for optimization of real time building operation.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
HRZZ-UIP-2020-02-9636 - Distribuirano upravljanje za dinamičko gospodarenje energijom u složenim sustavima naprednih gradova (DECIDE) (Lešić, Vinko, HRZZ - 2020-02) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb