Master Thesis - Decoding Occupancy: Classifying User Activity from Building Power Consumption with Machine Learning

At the Institute of Climate and Energy Systems Engineering (ICE-1) we focus on the development of models and algorithms for simulation and optimization of decentralized, integrated energy systems. Such systems are characterized by high shares of renewable energies and increasing sector coupling, which leads to high spatial and temporal variability of energy supply and demand as well as a high degree of interdependence of material and energy flows. Our research at the ICE institute aims to provide scalable and faster-than-real-time capable methods and tools that enable the energy-optimal, cost-efficient and safe design and operation of future energy system.

Your Job

The transition toward smart, energy-efficient buildings requires a deep understanding of how occupants actually use space and energy over time. Office buildings generate rich, continuous streams of power consumption data that implicitly encode patterns of human activity like the presence, movement between rooms, equipment usage, and occupancy density. Yet, this signal remains largely untapped for automated interpretation.

Inferring user activity directly from aggregate or sub-metered power consumption is a challenging inverse problem: activity signatures are noisy, non-stationary, and often ambiguous, especially when multiple occupants or devices contribute to the same load profile. Robust classification requires models that not only predict activity states accurately, but also express calibrated uncertainty, since misclassifications can lead to poor energy management decisions or inappropriate building automation responses.

The goal of this project is to design and validate a machine learning framework for classifying user activity in office buildings using power consumption data, with a focus on probabilistic approaches such as Gaussian Processes that provide principled uncertainty quantification. Your task in detail:

Design a data pipeline to extract and preprocess activity-relevant features from monitored building power consumption data
Develop a classification algorithm (e.g., based on Gaussian Processes or related probabilistic models) to infer user activity states from power signals
Validate and benchmark your method against alternative classifiers on real building datasets
Quantify and formalize uncertainty estimates to support reliable deployment in real-world building management systems

For further information on the project you can contact your future superior: https://www.fz-juelich.de/profile/buechel_m

Your Profile

Excellent university degree (Bachelor) in field of Data Science or a comparable field i.e. Electrical Engineering, Computer Science/Engineering, Physics
Strong mathematical background
Interest in energy systems, power grids and its components
Excellent knowledge and experience in programming Python
Excellent knowledge and experience in machine learning
Experience with git is welcome
Excellent ability for cooperative collaboration
Very good command of written and spoken English with extensive vocabulary is required (at least B2 level according to the ), ideally supported by a certificate confirming the language level
Prior German knowledge is not strictly required

Our Benefits for You

We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We support you in your work with:

Meaningful Tasks: Your thesis deals with a future-oriented, socially relevant topic with direct practical relevance in an international environment
Practical relevance: With us, you will gain valuable practical experience alongside your studies and actively participate in interdisciplinary projects
Scientific environment: You can expect excellent scientific equipment, modern technologies, and qualified support from experienced colleagues
Personal responsibility: You organize your tasks independently—from preparation to implementation
Work-life balance: We offer flexible working hours to help you balance your professional and personal life. You also have the option of flexible working (in terms of location), which is generally possible after consultation and in line with upcoming tasks and (on-site) appointments
Flexibility: Flexible working hours make it easier for you to balance work and study
Campus experience: Our research campus in the countryside creates ideal conditions for collegial exchange and sporting activities right on site. Our cafeteria offers a wide range of options—you can enjoy a relaxing lunch break with a lake view
Fair remuneration: We will pay you a reasonable remuneration for your thesis

In addition to exciting tasks and a collegial working environment, we offer you much more:

We welcome applications from people with diverse backgrounds, e.g. in terms of age, gender, disability, sexual orientation / identity, and social, ethnic and religious origin. A diverse and inclusive working environment with equal opportunities in which everyone can realize their potential is important to us.

The following links provide further information on diversity and equal opportunities: and on specific support options for women:

Place of Employment: Jülich

Start Date: To the next possible date

Salary: We will pay you a appropriate remuneration for your thesis

Application Deadline: The position will be published until it is successfully filled

Index number: 2026M-0602