Artificial Neural Networks for Predicting Cooling Load Reduction using Roof Passive Cooling Techniques in Buildings
Main Article Content
Abstract
Two identical prototype rooms having dimension 1m×1m×1m, were constructed using brick work. RCC roofs having
thickness of 100 mm were constructed on both rooms. Two roof passive cooling strategies (e.g., roof pond, insulation over the
roof) were applied on one of the test rooms one by one. The other room was kept with bare roof. The results show that the average
% reduction of roof cooling load was found to be 45 %., 30%, using roof pond, using insulation (thermocol) respectively.
The objective of this work is to train an artificial neural network (ANN) to learn to predict the reduction of cooling load
of buildings. Five training algorithms traincgb, traingdx, traingda, trainlm, and trainsc were used to create an ANN model. An
ANN has been trained based on number experimental data of cooling load. The network output is reduction in heat gain though
roof. The Intelligent model predicts reduction in cooling load with accuracy, more than 90%. The accuracy of the prediction could
be improved by more input data. The results show that the predicted data is in good harmony with the experimental data, which
indicates artificial neural network is a novel and reliable method to predict reduction in cooling load.
Â
Â
Keywords: Artificial neural network, Cooling-load reduction; Roof cooling; passive cooling, energy saving.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.