Premium
Modelling of residential energy consumption at the national level
Author(s) -
Aydinalp M.,
Ugursal V.I.,
Fung A.S.
Publication year - 2003
Publication title -
international journal of energy research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.808
H-Index - 95
eISSN - 1099-114X
pISSN - 0363-907X
DOI - 10.1002/er.887
Subject(s) - energy consumption , artificial neural network , consumption (sociology) , computer science , regression analysis , stock (firearms) , engineering , artificial intelligence , machine learning , mechanical engineering , social science , sociology , electrical engineering
Three methods are currently used to model residential energy consumption at the national level: the engineering method (EM), the conditional demand analysis (CDA) method, and the neural network (NN) method. While the use of the first two methods has been established over the past decade for residential energy modelling, the use of NN method is still in the development and verification phase. The EM involves developing a housing database representative of the national housing stock and estimating the energy consumption of the dwellings in the database using a building energy simulation program. CDA is a regression‐based method in which the regression attributes consumption to end‐uses on the basis of the total household energy consumption. The NN method models the residential energy consumption as a neural network, which is an information‐processing model inspired by the way the densely interconnected, parallel structure of the brain processes information. In this paper, the three methods are briefly described and a comparative assessment of the three methods is presented. Copyright © 2003 John Wiley & Sons, Ltd.