Master-Thesis: Machine Learning-based Heating Curves for Heat Producers in District Heating Networks

Fraunhofer-Gesellschaft; Bochum; Hybrid; EUR 30.000 - 50.000; Vollzeit

Zusammenfassung

Eine innovative Forschungseinrichtung sucht einen Masterstudenten, um an einem spannenden Projekt zur Optimierung von Fernwärmenetzwerken zu arbeiten. In dieser Rolle werden Sie mathematische Modelle und maschinelles Lernen anwenden, um die Effizienz von Heizkurven zu verbessern. Sie werden in einem dynamischen Team arbeiten, das Ihre Entwicklung unterstützt und Ihnen die Möglichkeit bietet, praktische Erfahrungen zu sammeln. Diese Position bietet flexible Arbeitszeiten und die Möglichkeit, remote zu arbeiten, während Sie gleichzeitig wertvolle Kenntnisse in einem zukunftsorientierten Bereich erwerben. Bewerben Sie sich jetzt und gestalten Sie die Zukunft der Energieinfrastruktur mit!

Leistungen

Attraktive Vergütung

Flexible Arbeitszeiten

Gut ausgestattete technische Infrastruktur

Individuelle Anleitung und Mentoring

Qualifikationen

• Eingeschrieben in ein Masterprogramm in Ingenieurwesen oder verwandten Bereichen.
• Gute Kenntnisse in mathematischer Modellierung und Simulation.

Aufgaben

• Literaturrecherche zu mathematischen Modellen und Maschinenlernen.
• Implementierung eines Modells für Fernwärmenetzwerke.

Kenntnisse

Mathematische Modellierung

Simulation dynamischer Systeme

Maschinenlernen

Deep Learning

Programmierung (Julia, Python, C++)

Ausbildung

Masterstudium in Ingenieurwesen

Masterstudium in Mathematik

Masterstudium in Energietechnik

Jobbeschreibung

The Fraunhofer Research Institution for Energy Infrastructures and Geothermal Energy IEG conducts research at seven locations in the fields of integrated energy infrastructures, geothermal energy and sector coupling for a successful energy transition. Our research institute conducts applied research, develops innovative technologies for public and industrial clients and translates these into marketable products and processes.

In light of the conclusions presented in the Heat Roadmap Europe, it is evident that the collective heat demand across 27 European countries constitutes approximately 50% of the final energy consumption. Consequently, the heat sector takes a pivotal role influencing European CO2 emissions, underscoring the imperative for a renewable energy driven heat supply to effectively address the challenges posed by global warming. In this context, district heating networks (DHNs) play a major role since they can realize fully decarbonized heat supply utilizing various distributed heat sources. The principle of operation of a DHN is the transport of water heated by the decentralized producers to the consumers, who can extract heat from this water and thereby lower the water temperature. The state-of-the-art (SoA) operation of a producer is primarily characterized by the temperature that the producer injects into the DHN, i.e., the producer's supply temperature. The set point for the supply temperature is often derived from a heating curve that defines a static correlation between measurable parameters, e.g. the ambient temperature, and the set point for the supply temperature.

Compared to the SoA operation utilizing static heating curves, optimization-based predictive operating strategies (OBPOSs) promise better performance. However, a very limited degree of digitalization in many DHNs makes it hard or even impossible to handle the signals needed for implementing an OBPOS. Nevertheless, mathematical models of DHNs allow to simulate the behavior of DHNs under predictive operation.

The main objective of this master thesis is to investigate whether the resulting simulation data can be used for the training of ML-based controllers that approximate OBPOS and require less implementation effort.
The master thesis will be supervised by Fraunhofer IEG scientists at the Bochum or Cottbus sites. If you are interested in this master thesis in an open and diverse team and want to build the bridge from applied to basic research, apply now!

What you will do

• Literature review on mathematical modeling and operation of district heating networks.
• Literature review on machine and deep learning methods for the prediction of heating curves or similar objectives.
• Implementation of a district heating network model including static heating curves as well as optimization-based operating strategies. The generated data will be used for training of a neural network.
• Setup of a machine learning-based heating curve using different suitable algorithms to approximate optimal producer’s supply temperature set points.
• Simulation case study to evaluate performance.
• Documentation of the results.

What you bring to the table

• Enrolled in a Master's programme in Engineering, Mathematics, Energy technology, or other STEM programs.
• Good knowledge of mathematical modeling or/and simulation of dynamical systems or/and machine and deep learning methods.
• Good programming skills, e.g. Julia, Python, C++.

What you can expect

• Practice-oriented work environment that complements your studies with an attractive remuneration.
• Supervisors who will strengthen and support you to become successful.
• Targeted and individual guidance and mentoring.
• Well-equipped technical infrastructure and flexible working hours at IEG in Cottbus.
• Flexible working hours that fit in with your studies. Possibility to work remotely.

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Remuneration according to the general works agreement for employing assistant staff.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Interested? Apply online now. We look forward to getting to know you!

If you have any questions about this position, please contact:

Henning Knauer and Max Rose

Contact by mail

If you have any questions about the application process, please contact:

Philipp Steinborn

Phone: [phone]

Contact by mail

Fraunhofer Research Institution for Energy Infrastructures and Geotechnologies IEG

www.ieg.fraunhofer.de

Requisition Number: 78954 Application Deadline: 04/30/2025