| Author: | Wong, Kin Chuen |
| Title: | Optimizing the energy efficiency of chillers in buildings via machine learning |
| Advisors: | Yiu, Man Lung Ken (COMP) |
| Degree: | Eng.D. |
| Year: | 2025 |
| Department: | Department of Computing |
| Pages: | 137 pages : color illustrations |
| Language: | English |
| Abstract: | This thesis presents a comprehensive study on enhancing the Coefficient of Performance (COP) of chillers in buildings through the modification of chiller sequencing control using machine learning techniques. The research focuses on developing a predictive control system that optimizes the operation of chillers to match the cooling load demand, thereby reducing energy consumption and improving overall system performance. The study begins with a detailed analysis of the current state of air conditioning systems and the challenges associated with traditional chiller control methods. It then explores various machine learning models for predicting cooling loads and chiller energy performance, including Support Vector Regression (SVR), Gradient Boosting Regressors (GBR), and Extreme Gradient Boosting (XGB). The research employs Genetic Algorithms (GA) to optimize these models, ensuring the optimal COP for the chiller plant. The proposed optimization framework is validated using historical data from a 9-storey educational building in Hong Kong. The results demonstrate significant improvements in energy efficiency, with the optimized chiller sequencing control achieving a higher COP compared to traditional methods. This research contributes to the field of energy management by providing a practical and scalable solution for optimizing chiller operations in commercial and industrial buildings. The findings highlight the potential of data-driven approaches in achieving sustainable and energy-efficient building operations. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8587.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 7.93 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/14135