Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.contributor | Department of Building Services Engineering | en_US |
| dc.creator | Wong, Hon-cheung | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/3639 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Simulations of building energy end use by artificial neural networks | en_US |
| dcterms.abstract | Simulation is always an attractive challenge for researchers. Precise simulation of electricity consumption is crucial for planning and implementing energy policies, and energy saving measures. Artificial neural network technique has a great potential for energy consumption prediction. The aim of this study is to identify the feasibility of using artificial neural networks to simulate energy end-use in local buildings. Developing and executing neural network models in a convenient computer spreadsheet environment of 'Microsoft Excel' together with a 'Microsoft Excel VBA' programme is demonstrated and encouraged. The computer spreadsheet software is mainly used as a data management tool, and the computer programme is used to build up, train and test neural network models. This approach facilitates manipulation and modification of developed models. Several potential preliminary models are developed for simulation of the electricity end uses in public and private residential buildings. Data sets released from the Electrical and Mechanical Services Department in the period from 1984 to 1995 are used for training of neural network models, and the trained model is tested with the data set of the year of 1996. All aspects of neural networks including training method, key parameters, and configurations are explored. Through tests, two optimal models emerge. Despite the small data sets for calibration, the performances of optimal models are comparatively acceptable. The developed models have to be updated upon more data are ready. The same approach is also utilized to develop a neural network for predicting electricity consumption of a chiller plant. The performance is considered acceptable. The approach for development of neural networks presented in this dissertation can be applied in other energy predictions. | en_US |
| dcterms.extent | 1 v. (various pagings) : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2001 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Buildings -- Energy consumption | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b1597800x.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.65 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/200/3639