Title :
Neural networks for energy flows prediction in facility systems
Author :
Frosini, L. ; Petrecca, G.
Author_Institution :
Dept. of Electr. Eng., Pavia Univ., Italy
Abstract :
A procedure for the short-term prediction of the thermal energy consumption of a hospital is shown in this paper. First, linear ARX models are built in order to obtain information on the influence of the input variables on the output of the system. Therefore, nonlinear models based on feedforward neural networks (NNARX) are built using the information provided by the linear estimate. The results obtained from the ARX and NNARX models are compared, concluding that NNARX models provide better results than ARX models, but the analysis of ARX models is necessary to obtain guidelines in the choice of the best regression vector as input for the neural models
Keywords :
autoregressive processes; biomedical engineering; environmental engineering; feedforward neural nets; forecasting theory; heat transfer; load forecasting; power consumption; power engineering computing; space heating; NNARX models; energy flow prediction; facility systems; feedforward neural networks; hospital; input variables; linear ARX models; linear estimate; nonlinear models; regression vector; short-term prediction; system output; thermal energy consumption; Economic forecasting; Energy consumption; Energy management; Feedforward neural networks; Hospitals; Intelligent networks; Load forecasting; Neural networks; Power generation economics; Thermal management;
Conference_Titel :
Soft Computing Methods in Industrial Applications, 1999. SMCia/99. Proceedings of the 1999 IEEE Midnight-Sun Workshop on
Conference_Location :
Kuusamo
Print_ISBN :
0-7803-5280-7
DOI :
10.1109/SMCIA.1999.782713
