Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Building Environment and Energy Engineering | en_US |
| dc.contributor.advisor | Fu, Xiao (BEEE) | en_US |
| dc.creator | Gao, Meng | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/14112 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Comparative evaluation of machine learning algorithms for building HVAC electricity demand prediction | en_US |
| dcterms.abstract | The building sector uses approximately 40% of the energy of the word, with heating, ventilation, and air conditioning systems using nearly half of the energy. Since the building sector accounts for a large portion of energy demand, accurate power load forecasting is particularly important for energy management and optimization of energy systems. While existing studies have developed some independent forecasting models, few studies have compared the predictive capabilities of single models. This study addresses this gap by providing a systematic evaluation framework that rigorously examines the performance of algorithms in terms of temporal pattern recognition, adaptability to load changes, and computational efficiency. The framework provides a standardized method for comparing forecasting techniques while clarifying their respective strengths and limitations in different building energy management contexts. | en_US |
| dcterms.abstract | This study compares the prediction results of the deep neural network (DNN) and the long short-term memory network (LSTM) model for the same building, revealing their performance differences under different indicators. Results show that the LSTM model shows better modeling ability and its prediction accuracy is significantly improved compared with the DNN. In contrast, the DNN has a simpler structure but is less efficient and less sensitive in capturing dependencies. | en_US |
| dcterms.abstract | At the same time, this study systematically evaluates the performance characteristics of both deep neural network (DNN) and long short- term memory (LSTM) models under varying experimental conditions. The LSTM model has always shown excellent performance and efficiency in HVAC power demand forecasting, while the DNN model is not the best choice in specific use cases, but it does not rule out that it is more suitable for other forecasts. | en_US |
| dcterms.extent | vii, 47 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2025 | en_US |
| dcterms.educationalLevel | M.Eng. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8567.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.61 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/200/14112