Tools
Tools
Hagavane, Pranav Pramod (2024) Evaluating the Impact of Environmental Conditions on Heat Pump Performance using Machine Learning Models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (675kB) | Preview |
Abstract
The heat pump market is growing every year with a significant growth rate globally and the importance of efficient heating is also increasing as heat pumps with high efficiency has the potential to reduce energy consumption and greenhouse gas emissions. The performance of the heat pump is dependent of the heat sources as well as the heat sink, and the existing studies has primarily focused on considering only the heat sources, which does not provide a compete understanding on the performance on heat pump. The study tries to address this gap in the existing literature by considering not only different heat sources but also different heat sinks, such as radiators, floor heating systems, and water heating systems, which is associated with each heat source like air source heat pumps can have any of the three heat sinks, to predict and identify their impact on the COP of the heat pumps. By developing a model which predicts the COP accurately of a heat pumps based on the factors weather conditions, can benefit different aspects such as residential and commercial property settings, guiding the design and selection of the heat pumps for different climatic conditions. This research project implements various machine learning and deep learning models out which the Gradient Boost and the voting regressor achieved highest accuracy of 96%. Deep learning models, such as LSTM and MLP, showed slightly lower performance, with the accuracy of 84% and 85%. These findings indicates how effective the ensemble machine learning methods are in accurately predicting the Coefficient of Performance (COP) for heat pumps.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Rustam, Furqan UNSPECIFIED |
| Subjects: | G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 18 Aug 2025 15:39 |
| Last Modified: | 18 Aug 2025 15:39 |
| URI: | https://norma.ncirl.ie/id/eprint/8574 |
Actions (login required)
 |
View Item |