Please use this identifier to cite or link to this item:
|Title:||Artificial neural networks for the prediction of the energy consumption of a passive solar building||Authors:||Bojic, Milorad
Kalogirou, Soteris A.
|Keywords:||Artificial Neural Networks (ANN);Energy consumption||Issue Date:||2000||Publisher:||Elsevier B. V.||Source:||Energy, Vol. 25, no. 5, 2000, pp. 479-491||Abstract:||Artificial neural networks (ANNs) have been used for the prediction of the energy consumption of a passive solar building. The building structure consists of one room with an inclined roof. Two cases were investigated, an all insulated building and a building with one wall made completely of masonry and the other walls made partially of masonry and thermal insulation. The investigation was performed for two seasons: winter, for which the building with the masonry-only wall is facing south, and summer, for which the building with the masonry-only wall is facing north. The building's thermal behaviour was evaluated by using a dynamic thermal building model constructed on the basis of finite volumes and time marching. The energy consumption of the building depends on whether all walls have insulation, on the thickness of the masonry and insulation and on the season. Simulated data for a number of cases were used to train an artificial neural network (ANN) in order to generate a mapping between the above easily measurable inputs and the desired output, i.e., the building energy consumption in kWh. The simulated buildings had walls varying from 15 cm to 60 cm in thickness. The objective of this work is to produce another simulation program, using ANNs, to model the thermal behaviour of the building. A multilayer recurrent architecture using the standard back-propagation learning algorithm has been applied. The results obtained for the training set are such that they yield a coefficient of multiple determination (R2 value) equal to 0.9985. The network was used subsequently for predictions of the energy consumption for cases other than the ones used for training. The coefficient of multiple determination obtained in this case was equal to 0.9991, which is very satisfactory. The ANN model proved to be much faster than the dynamic simulation programs.||URI:||http://ktisis.cut.ac.cy/handle/10488/206||ISSN:||0360-5442||DOI:||http://dx.doi.org/10.1016/S0360-5442(99)00086-9||Rights:||Copyright © 2000 Elsevier Science Ltd. All rights reserved.||Type:||Article|
|Appears in Collections:||Άρθρα/Articles|
Show full item record
checked on Aug 20, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.