This new programme provides an academically leading and industrially relevant study of energy systems through the lens of data analytics.
On this page:
The Energy Systems and Data Analytics MSc (ESDA MSc) is the first programme of its kind in the UK, combining the study of Energy Systems with Data Science. As an ESDA student, you will gain a multi-sector, multi-vector understanding of Energy Systems, while developing advanced statistical and machine learning skills and getting practical experience of data analysis.
The programme is aimed at students with a quantitative background who have an interest in energy and are motivated by the use of data science to solve sustainability problems. You will gain skills sought after by industry allowing you to become a leader and innovator in the energy sector, from established large scale utilities and data science companies to innovative new start-ups.
This advanced degree programme is designed to provide a broad understanding of energy systems, statistics, programming, energy use in the built environment, energy use in the transport sector and the role of data and advanced analytics in solving relevant sustainability problems.
For key information, including tuitions fees and application dates, visit the UCL Graduate Prospectus.
- Learning outcomes
Studying in an interdisciplinary, collaborative learning environment, you will learn, at both an introductory and advanced level, about:
- Statistics and programming for analysis of energy data
- Multi-vector, multi-sector understanding of energy systems
- Issues and challenges of global energy use, including climate change
- Fields of energy system and econometric modelling
- Energy use in transport; shipping, aviation and urban transport
- Energy use in the built environment from building to cities
- The role of data in addressing problems of sustainability
The ESDA MSc offers a number of both compulsory and optional modules, including a dissertation.
- Energy Systems
This core module anchors the ESDA MSc on an interdisciplinary view of energy systems. It thus gives the domain breadth for the subsequent data and analytics methods module to be applied to, and provides signposts to these modules with real world examples for the discussion of subsequent analytical techniques.
The Energy Systems module will encompass the linkages and interactions between the upstream to downstream elements of the full energy system: covering resource extraction, production and trade; upstream processes (power generation, refineries, bio and hydrogen production); energy infrastructures (electricity, natural gas and heat), and major energy demand sectors (industry, commercial, residential, transport). The module will progressively examine the energy systems through a series of disciplinary lenses – environmental, technological, economic, political and societal.
Topics include: Environmental, technological, economic, political and societal aspects of energy systems, Key policy mechanisms for energy systems – innovation, pricing and market design, Inter-temporal nature of energy systems, Multi-level spatial aspects of energy supply-distribution-demand, Introduction of tools used to design policy and make investment decisions
Assessment: One piece of written coursework 3000-words (100%)
- Statistics for Energy Data Analysis
This module focuses on the theory and mathematics of the statistical methodology students require to carry out advanced data analysis of energy related data sets. It introduces students to the different complexities associated with energy data, familiarizing them with issues such as heterogeneity, seasonality and non-linear behaviour to motivate the need for advanced methods such as clustering, classification and non-linear regression. The theoretical principles underpinning many of the most powerful state of the art statistical approaches being used in machine learning research will be covered including discussion of their limitations, where they break down and how the methods fit together in the broader context to complement each other and form a tool kit for analysis.
Topics include: Bayesian Statistics, Machine Learning, Linear and Non-linear regression methods, Clustering and Classification Neural networks, Application of methods to problems in energy
Assessment: 2-hour unseen examination (80%)
Problem sets (20%)
Examples of reading material:
Elements of Statistical Learning. Hastie, Tibshirani and Friedman. 2009 Pattern Recognition and Machine Learning. Bishop. 2006.
Machine Learning a Probabilistic Approach. Murphy. 2012.
- Energy Data Analysis
This module focuses on teaching the practical programming skills required for analysis of energy data sets. Students will be taught the fundamental concepts of programming through the leading data science programming language R. They will also be exposed to other languages and software tools such as SQL, Python and Gephi and gain an understanding of when and where each is appropriate, for example using SQL for database access.
Topics covered: Fundamental concepts in programming, Working with data, manipulation and cleaning, Strategies for handling missing data, The art of data visualization, Deploying models
- Energy Data Analysis in the Built Environment
The Built Environment is a significant component of an Energy System and this module is dedicated to teaching students about energy use in the Built Environment and how advanced analytics can be used to understand, predict and influence this demand. The content of the module will be built around four themes; services, fabric, people and scale. Each theme covers a different dimension of energy use in the built environment using associated data. Services will detail the many different services for which energy is required, heating, lighting, etc and introduces Non-Intrusive Load Monitoring as a way of using advanced analytics to better understand this area. Fabric discusses the influence of building materials on a building’s energy performance and the potential impacts of retrofitting and refurbishment. People’s occupancy and behavioural patterns significantly affect both the quantity and the temporal variation of energy demand and smart meter data will be used to illustrate this variation. Finally, scale will concentrate on the different resolutions at which energy use in the Built Environment can be studied; from an individual building to an entire city and the complexities and challenges involved. Combining these four themes and how they interact will give students a rich understanding of energy use in the built environment within a data driven framework.
Assessment: 3000-word essay (100%)
- Energy and Transport Analytics
This module focuses on the role of the transport sector in the energy system and the analysis of transport energy demand. The module will start with combine teaching on vehicle-level energy demand and fleet-level analytics, to develop characterisations of current and historical transport energy demand. The module will also deliver teaching on the use of scenario modelling to estimate how identified drivers might result in different outcomes for future transport energy demand. The module will build on mathematical and statistical methodologies taught in earlier modules, reinforcing learning by providing application cases and opportunities to gain experience with these methods. The module will discuss the impact of big data on the transport sector, how it has enabled new modes and technologies such as Uber etc. and the potential for advanced analytics to continue to solve problems of sustainability in this sector.
Assessment: 3000-word essay (100%)
- Spatial Analysis of Energy Data
The purpose of this module is to introduce you to energy modelling analysis where there are spatial and temporal elements which can reveal important and relevant relations between energy potential, resources and demand.
Geospatial energy analysis does not only brings an understanding of the energy potential of a particular region but it also gives a solid base for feasibility studies, policy making and socio-environmental impacts. This cutting-edge discipline uses available georeferenced data from sensors, records, models and meters to recognise regional and global patterns that can be used to combat climate change and energy poverty.
This module will provide students with core GIS (Geographic Information System) skills using QGIS and R (the module assumes that you are familiarised and skilled using R). It will give students both, technical and analytical skills. To achieve this, the module will combine theoretical (lecture) and practical (tutorials) knowledge with surgeries. From week six, invited guests will share their experience and knowledge with geospatial analysis in the different energy sectors.
The dissertation is a core part of the MSc ESDA. The dissertation project is an opportunity for students to put the skills and knowledge acquired during the programme into practice through a piece of original research. Each student works with a dissertation supervisor – a UCL researcher with expertise in the field – and develops a unique project.
A choice of two optional modules are available from the list below:
- Introduction to System Dynamics Modelling
- Advanced Energy-Environment-Economy Modelling
- UK Energy and Environment Policy and Law
- Energy, Technology and Innovation
- Econometrics of Energy Markets
- Other teaching staff
Energy Systems and Data Analytics Class of 2019
ESDA is a one of kind MSc., it offers the rigour of statistics to understand the promise and perils of data analytics and machine learning, while providing you a holistic view of the energy systems: transport, built environment and the electricity system. It is conducted by an interdisciplinary set of lectures from UCL’s Energy Institute and attended by a diverse (and very friendly!) group of students. All of this combined with a solid industry approach to prepare you for the challenges to achieve a sustainable energy future.
Simon Perez Arango, UCL Energy Systems and Data Analytics Student 2019
Xavier Mamo, Director of the EDF Energy R&D UK Centre
The ESDA MSc addresses a key skills gap in the Energy Industry for graduates with expertise in energy systems and also cutting-edge data analytics skills.
- About EDF Energy
EDF Energy is one of the UK’s largest energy companies and its largest producer of low-carbon electricity. A wholly owned subsidiary of the EDF Group, one of Europe’s largest energy groups, EDF Energy generates around one fifth of the UK’s electricity. It employs around 15,000 people and supplies electricity and gas to roughly 5.5 million residential and business customers, making it the UK's largest supplier of electricity by volume.
Oliver Rix, Partner at Baringa
We see the combination of energy systems and data analytics as crucial in providing decision support for policy, investments and strategy development in the future, and the ESDA MSc mirrors our own focus on the development of leading practices in energy systems and data science, and the ability to combine these capabilities effectively.
- About Baringa Partners
Baringa Partners is an independent business and technology consultancy. They help businesses run more effectively, reach new markets and navigate industry shifts. Their Energy Practice is a specialist economic and commercial energy consultancy, advising clients on investments, strategy, policy and regulation across Europe’s power, gas and carbon markets.
ESDA Potential Energy Scholarship
The ESDA Potential Energy Scholarship is open to all students who hold an offer (conditional or unconditional) for the Energy Systems and Data Analytics MSc.
The Bartlett Master's Scholarships
The Bartlett, UCL’s Faculty of the Built Environment, offers 10 scholarships for MSc, MPlan, MRes, MA and MArch students, each worth £10,000, to be used either as partial fee remittance for study or as a bursary to cover living costs.
UCL has a range of other scholarships, loans and other funding opportunities available to help prospective students with their studies.
We offer expertise from the UCL Energy Institute and across The Bartlett Faculty of the Built Environment, including:
- Energy in transport; shipping, aviation and urban transport
- Energy use in the built environment, from individual buildings to cities
- Advanced analytics and machine learning applied to energy data
- Green economy and innovation
- Energy efficiency
- The opportunity to gain in-depth practical expertise in several specific areas of analysis related to the above topics.
We also offer:
- Leading centres for research into energy systems
- In-depth relationships with UK government agencies, regulators and advisory bodies.
- Close connections to industry – utilities, consultancies, start-ups and other businesses, as well as wider links to non-governmental organisations and think tanks.
- For key information, including how to apply, visit the UCL Graduate Prospectus
- Read more industry views of the Energy Systems and Data Analytics MSc
- For admissions enquiries, please email firstname.lastname@example.org
- For further questions about the programme, please contact the Course Director, Dr Aidan O'Sullivan: email@example.com