Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Building Environment and Energy Engineering | en_US |
| dc.contributor.advisor | Lu, Lin Vivien (BEEE) | en_US |
| dc.creator | Lan, Yifan | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13308 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Deep reinforcement learning for energy-saving control in building/building group’s HVAC system | en_US |
| dcterms.abstract | In modern society, the energy consumption of the building industry and the resulting carbon dioxide emissions are becoming increasingly severe. This has become a strategic goal of energy conservation and emission reduction worldwide. According to the United Nations, the construction industry accounts for no less than 30% of society's total energy consumption and carbon emissions. Due to its direct impact on the indoor heating and cooling environment, the energy consumption of HVAC system operation accounts for a certain proportion of the total energy consumption of buildings. In order to achieve the goal of sustainable development and carbon neutrality, finding effective ways to reduce the energy consumption of HVAC systems is necessary. | en_US |
| dcterms.abstract | With the development of computer science technology, the deep reinforcement learning algorithm (DRL) plays an increasingly important role in various industries, including energy-saving control in construction occupation. DRL algorithms can analyze large inputs to determine the most effective action to achieve the desired goal. Numerous examples have demonstrated the feasibility of applying DRL algorithms in energy-saving control of HVAC systems. This project will utilize two classic DRL algorithms, Deep Q-learning Network (DQN) and Deep Deterministic Policy Gradient (DDPG). | en_US |
| dcterms.abstract | The research objects of this dissertation are the typical construction model of a 25-story office building in Hong Kong and its HVAC energy system, using SketchUp software for the development of a typical construction model. The design of the typical office building's HVAC system and the calculation of its energy consumption are done by OpenStudio software based on EnergyPlus software. After obtaining the data on energy consumption and the working situation of the HVAC system model, design DQN and DDPG algorithms for the HVAC system using the Python language and train the algorithms. After that, apply the trained algorithms to the HVAC system and discuss the difference between the results with and without the DRL algorithm in terms of energy consumption of the HVAC system model to support the feasibility of using the DRL algorithm to reduce energy consumption. Then, with the project research results and other materials and references, briefly discuss the feasibility of applying the DRL algorithm for building group's HVAC system's energy-saving control. | en_US |
| dcterms.extent | ix, 54 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2024 | en_US |
| dcterms.educationalLevel | M.Eng. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Air conditioning -- Automatic control | en_US |
| dcterms.LCSH | Buildings -- Energy conservation | 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 | |
|---|---|---|---|---|
| 7755.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.86 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/200/13308