Aim:
This research aims to develop an integrated System Dynamics Machine Learning (SDML) model to simulate the inter-dependencies among the hard and soft variables of energy consumption in buildings. As a sociotechnical problem, the research will explore the intrinsic interrelationship between buildings, occupants and environment systems. The study will identify ‘cause and effect’ relationships among the components of these systems and simulate their behaviour.
The proposed SDML model will provide policy makers with a decision support tool upon which different scenarios regarding energy consumption and carbon emission in buildings can be tested before implementation.
Context:
Various models have been developed to analyse the impact of energy initiatives and policies on buildings performance. These models can be classified as disciplinary and multidisciplinary models comprising variables related to technology, economic, sociology, occupants’ behaviour and climate. Even for those multidisciplinary models, there are limitations in simulating the complexity of the interrelationships among the considered variables.
A system-based approach will be adopted in this research to overcome this limitation and to simulate the socio-technical aspects of energy consumption in buildings. For such purpose, System Dynamics (SD) techniques will be utilised. The research will also test different scenarios to upgrade building technologies based on multi-objectives optimisation of energy consumption. Various technology variables will be considered such as insulation levels, lighting controls, air tightness, and system efficiencies. In addition, various constraints will be considered such as building fabric/characteristic/usage, available budget, and the economic feasibility and payback of energy saving.
Traditionally, multi-objectives optimisation is conducted to select an appropriate retrofit technology(ies) using integrated optimisation algorithm and Building Performance Simulation tools. Many studies reported the time-consuming and costly procedures for conducting these optimisation tests specially when considering large number of variables and technology options. In dealing with such problem to predict energy performance of buildings and conduct the multi-objectives optimisation, data-driven models that utilise historical data of energy usage and building features are proposed. Hence this research will utilise Machine Learning (ML) algorithms in integration with the SD model.
As literature shows that the use of ML algorithms to predict buildings performance have been limited to the use of elementary physical characteristics and climate features, the integration of SD and ML in the proposed model will overcome this limitation. In addition, ML algorithms can help generate inputs for SD models and analyse model outputs. While improving energy performance of new buildings is highly important, it has been addressed that refurbishment of existing buildings will make the significant contribution in reducing carbon emission due to the percentage of existing to new buildings. In the UK, a recent study has reported that 15% of the non-residential building are receiving SBEM bands of F and G. Therefore, this study will focus on modelling energy performance for existing nondomestic buildings. The study will target the buildings stock in NI.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The following scholarship options are available to applicants worldwide:
These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.
Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.
Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 5 February 2021
12:00AM
Interview Date
April 2021
Preferred student start date
Mid-September 2021
Telephone
Contact by phone
Email
Contact by email