Thesis Work - Identifying distributed energy resources from consumption patterns

Are you a student looking to apply your knowledge to real-world solutions that support the energy transition? With us, you will have the opportunity to complete your thesis project close to the business, working alongside experienced specialists and tackling challenges where your ideas and perspectives can make a real difference.
About the Thesis Work
Vattenfall Research & Development (R&D) drives innovation to accelerate fossil freedom and create value across Vattenfall. The Customer Products & Solutions (CPS) Analytics Programme develops data-driven methods and AI-powered solutions to address challenges and opportunities within customer and energy-system domains. This thesis will be conducted within the Analytics Programme at Vattenfall R&D in close collaboration with the Data & Analytics group in Business Area Customers & Solutions in the Netherlands.
The growing adoption of distributed energy resources is transforming electricity production and consumption. Technologies such as electric vehicles, heat pumps, battery storage systems, and solar PV create new forecasting challenges while also enabling more flexible and efficient energy services. Better insight into these resources could help customers optimize energy use and flexibility while supporting a more reliable energy system.
The thesis will investigate how distributed energy resources can be identified from electricity consumption data using data-driven and machine learning approaches. The project will explore load disaggregation and classification techniques to detect characteristic consumption patterns associated with specific energy resources. Improved visibility of customer assets can support applications such as load forecasting, grid planning, flexibility markets, and customer-centric energy services.
The purpose of this thesis is to evaluate the feasibility and accuracy of identifying distributed energy resources from electricity consumption data. The student will:
Review relevant literature on load disaggregation and energy asset identification.
Develop and evaluate machine learning and statistical models for detecting distributed energy resources from consumption patterns.
Assess model performance, limitations, and uncertainty.
Provide recommendations for future implementation and research.
We are looking for 1 student who are about to complete their academic studies and are eager to apply their knowledge in a real-world setting through a thesis project at Vattenfall. You are someone who shares our values and identifies with our principles: Active, Open, Positive and Safety.
Currently enrolled in a Master’s programme in Data Science, Machine Learning, Statistics, Applied Mathematics, Computer Science, Engineering Physics, Energy Systems, or a related quantitative field.
Proficiency in English
Knowledge of statistical modelling and machine learning.
Experience with Python and commonly used data science libraries.
Experience with time-series analysis and predictive modelling.
Interest in energy systems, electrification, and the energy transition.
Master’s thesis, 30 ECTS credits.

Employment type
Contract

Work arrangement
No