Journal
ALEXANDRIA ENGINEERING JOURNAL
Volume 57, Issue 1, Pages 455-473Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.aej.2016.09.001
Keywords
Hybrid microgeneration system; Ground source heat pump; Photovoltaic thermal; Artificial neural network; Predictive control; Energy saving
Categories
Funding
- International Cooperation of Korea Institute of Energy Technology Evaluation and Planning (KETEP) - Korea Government Ministry of Knowledge Economy [20118520010010]
- Canadian government
- Republic of Korea government
- Korea Evaluation Institute of Industrial Technology (KEIT) [20118520010010] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
The use of artificial neural networks (ANNs) in various applications has grown significantly over the years. This paper compares an ANN based approach with a conventional on-off control applied to the operation of a ground source heat pump/photovoltaic thermal system serving a single house located in Ottawa (Canada) for heating and cooling purposes. The hybrid renewable microgeneration system was investigated using the dynamic simulation software TRNSYS. A controller for predicting the future room temperature was developed in the MATLAB environment and six ANN control logics were analyzed. The comparison was performed in terms of ability to maintain the desired indoor comfort levels, primary energy consumption, operating costs and carbon dioxide equivalent emissions during a week of the heating period and a week of the cooling period. The results showed that the ANN approach is potentially able to alleviate the intensity of thermal discomfort associated with overheating/overcooling phenomena, but it could cause an increase in unmet comfort hours. The analysis also highlighted that the ANNs based strategies could reduce the primary energy consumption (up to around 36%), the operating costs (up to around 81%) as well as the carbon dioxide equivalent emissions (up to around 36%). (C) 2016 Faculty of Engineering, Alexandria University. Production and hosting by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available