Masterarbeit – Predictive Maintenance & Environmental Monitoring In Microgenerator Swarms; M​/F​/D

fortiss is the research institute of the Free State of Bavaria for software-intensive system sand services with headquarters in Munich. The institute currently employs around 150 employees,who collaborate on research, development and transfer projects with universities and technology companies in Bavaria, Germany and Europe. Research is focused on state of the art methods, technique sand tools of software development, systems &service engineering and their application to reliable, secure cyber-physical systems, such asthe Internet of Things (IoT).

fortiss has thelegal structure of a non-profit limited liability company (GmbH). Its shareholders are the Free State of Bavaria (as majority shareholder) and the Fraunhofer Society for the Promotion of Applied Research.

To extend our research lines in our Architectures and Services for Critical Infrastructures team, we are offering a:
MSc Thesis on Graph neural networks for topology aware predictive maintenance and environmental monitoring in emerging renewable energy infrastructures – micro-hydropower device swarms (m/f/d)

In recent years, the landscape of energy distribution systems has undergone a remarkable transformation. The modernization and diversification of the energy networks has comewith severe challenges and opportunities, and theadvent of smart grids have initiated an era ofmassive data generation and exchange in this domain. Data from several measuring devices distributed across the network are now available,and this together with the power of modern machine learning techniques present opportunities for amore resilient, efficient, and sustainable energy infrastructure.

The aim of the project is to develop an automated process for robust and accurate predictive maintenance, diagnosis and environmental monitoring in an emerging form of renewable energy composed of a swarm of river hydropower plants. To this end, learning methods involving graph neural networks considering topological information, external knowledge sources must be researched. Our research relies on incorporating data from heterogeneous measuring devices at different locations and incorporate elements from previous work on fault localization in low and medium voltage energy grids.

• Review literature on graph neural networks state of the art
• Expanding methods from previous research on graph neural networks for fault localization inlow and medium voltage energy grids
• Scaling up and parallelizing simulation sand training e.g. via Cloud computing,Containerization and Virtualization Techniques(Cloud/Docker/Kubernetes/VMs)
• Scripting solutions to optimize data pipelines (Python/Bash)
• Integrating data from heterogeneous sensors on a 5G network
• Developing and improving Graph Neural Network Models for forecasting, diagnosis and predictive maintenance (Python/Pytorch/Matlab)
• Integrating river topology, environmental measurements in propagation models
• Code Versioning and Issue Management(Git)
• Training and co-developing new technique sand ML models
• Eventually co-authoring research papersand supporting dissemination tasks.

• Student of M. Sc. in Computer Science,Electrical Engineering or similar
• Knowledge in neural networks,machine-learning, ideally on graph neural networks too
• Self-motivated and structured way ofworking
• Good communication skills in English
• Availability to work on-site

• International and dynamic work environment
• Flexible schedule and work in convenient location
• Possibility to perform research in challenging and exciting topics in the field ofmachine learning and emerging renewable energy technologies

Did we catch your interest?

Please submit your application with a motivational statement, a detailed CV and acurrent transcript of records.

Curious, which TUM alumni are working in your field?

Enterpreneurs wanted! TUM support for prospective startups.