 An artificial neural network for predicting domestic hot water characteristicsChristian Barteczko-Hibbert, Mark Gillott and Graham Kendall International Journal of Low-Carbon Technologies, 2009, vol. 4, issue 2, 112-119 Abstract: Domestic hot water (DHW) in the UK accounts for ∼7.5% of all energy use. For manufacturers of heating and hot water appliances to be in a position to respond to patterns of demand a full understanding of the effect of user-defined DHW profiles, different DHW systems and heating technologies are essential. This paper presents the prediction of the temperature characteristics of drawn DHW using artificial neural networks (NNs). We demonstrate whether, based on one NN model, different hot water system temperature loads can be accurately predicted. Two NN models were constructed and examined on a total of three systems. Both models trained on their associated systems produced errors of <11%; however, both NN models, when presented with unseen systems, produced large single errors. NN model 2 gave the lowest error when compared with NN model 1. Copyright The Author 2009. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org, Oxford University Press. Date: 2009 Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:4:y:2009:i:2:p:112-119 Access Statistics for this article International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat More articles in International Journal of Low-Carbon Technologies from Oxford University Press |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.