Accessibility navigation

Building energy management and occupants’ behaviour-intelligent agents, modelling methods and multi-objective decision making algorithms

Jiang, L. (2017) Building energy management and occupants’ behaviour-intelligent agents, modelling methods and multi-objective decision making algorithms. PhD thesis, University of Reading

Text - Thesis
· Please see our End User Agreement before downloading.

[img] Text - Thesis Deposit Form
· Restricted to Repository staff only


It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.


In the UK, buildings contribute around one third of the energy-related greenhouse gas emissions. Space heating and cooling systems are among the biggest power consumers in buildings. Thus, improvement of energy efficient of HVAC systems will play a significant role in achieving the UK carbon reduction target. This research aims to develop a novel Building Energy Management System (BEMS) to reduce the energy consumption of the HVAC system while fulfilling occupants’ thermal comfort requirements. The proposed system not only considers the occupants’ adaptations when making decisions on the set temperature, but also influences occupants’ behaviours by providing them with suggestions that help eliminate unnecessary heating and cooling. Multi-agent technologies are applied to design the BEMS’s architecture. The Epistemic-Deontic-Axiologic (EDA) agent model is applied to develop the structure of the agents inside the system. The EDA-based agents select their optimal action plan by considering the occupants’ thermal sensations, their behavioural adaptations and the energy consumption of the HVAC system. Each aspect is represented by its relevant objective function. Newly-developed personal thermal sensation models and group-of-people-based thermal sensation models generated by support vector machine based algorithms are applied as objective functions to evaluate the occupants’ thermal sensations. Equations calculating heating and cooling loads are used to represent energy consumption objectives. Complexities of adaptive behaviours and confidence of association rules between behaviours and thermal sensations are used to build objective functions of behavioural adaptations. In order to make decisions by considering the above objectives, novel multi-objective decision-making algorithms are developed to help the BEMS system make optimal decisions on HVAC set temperature and suggestions to the occupants. Simulation results prove that the newly-developed BEMS can help the HVAC system reduce energy consumption by up to 10% while fulfilling the occupants’ thermal comfort requirements.

Item Type:Thesis (PhD)
Thesis Supervisor:Yao, R., Liu, K. and McCrindle, R.
Thesis/Report Department:School of the Built Environment
Identification Number/DOI:
Divisions:Science > School of the Built Environment
ID Code:68391
Date on Title Page:2016


Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation