Machine learning methods to manage the integration of heating systems into the wider energy system

Heat demand which has large seasonal variations and high morning peak ramp-up rates, is responsible for 44% of the total energy demand in the UK and mainly supplied through the natural gas grid. District energy systems with Seasonal Thermal Energy Storage (STES) can be affordable and more sustainable alternatives that can handle the high ramp-up rates and seasonal variations. However, existing systems are designed and operated independently from the wider energy system (electricity, cooling, industry and transport sectors), while the best solution (in terms of emissions reduction and cost) can only be found if all energy sectors are combined and coordinated. This multi-sector integration is an open challenge due to the nonlinear interactions between the different sectors as well as the significant computational complexity due to required spatial and temporal resolutions and model complexity.
 
In this project, the successful candidate will develop, implement and apply machine learning methods for the design and optimisation of district heating system with STES as part of the wider energy system. While the main focus is on using machine learning based surrogate models to link detailed CFD simulations with whole system models, there is scope to investigate other areas such as system control and demand/supply predictions.  
 
The candidate will develop a wide range of skills in heating systems with STES design and machine learning methods which will be widely applicable to the candidate’s future career. The project is linked to the EPSRC funded INTEGRATE project and the PhD student will be jointly supervised by Dr Daniel Friedrich at the School of Engineering at the University of Edinburgh and Prof Ben Hughes at the University of Hull.
 
The INTEGRATE project (Integrating seasoNal Thermal storagE with multiple enerGy souRces to decArbonise Thermal Energy) is a collaboration between the Universities of Edinburgh, Glasgow and Hull (EPSRC Reference: EP/T023112/1). The project will evaluate the potential of STES systems to facilitate the decarbonisation of heating and cooling while at the same time providing flexibility services for the future net-zero energy system. The project will develop a holistic and integrated design of district energy systems with STES by considering the interplay and coordination between energy supply and demand, seasonal thermal storage characteristics, and regulation and market frameworks. The results and models from the individual areas will be combined in a whole system model for the design and operation of smart district energy systems with STES.  

Closing date for applications: Position will remain open until filled.
Expected studentship start date: 1st October 2020 or as soon as possible thereafter.

 

Further Information: 

Closing Date: 

Monday, August 31, 2020

Principal Supervisor: 

Assistant Supervisor: 

Prof Ben Hughes, University of Hull

Eligibility: 

Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.

Essential background:  
•    2.1 or above (or equivalent) in Engineering, Mathematics, Energy Engineering, Informatics or similar
•    Programming in Python, Julia or other high-level language
•    Knowledge of machine learning methods
 
Desirable background:
•    Energy systems modelling and optimisation experience
•    CFD modelling
•    Building energy simulation
•    Knowledge about thermal energy storage

Funding: 

Tuition fees + stipend are available for Home/EU students (International students can apply, but the funding only covers the Home/EU fee rate)

Applications are welcomed from self-funded students, or students who are applying for scholarships from the University of Edinburgh or elsewhere

 

Further information and other funding options.

Informal Enquiries: