If not indicated otherwise, topics can be worked on in English or German.

If you are interested in working on one of these topics, please get in contact with the related colleague via email.
Please include a CV and academic record sheet (transcript of records) in your request.

Additional topics may be available on request. Please contact directly the scientific staff members dealing with with the field of research (see homepage) that fits your interests.

This also applies to requests for supervision of external theses or internships. Please note that we will only supervise these if the topic fits into our field of research and is of interest to us.

BT:  Bachelor's Thesis
MT: Master's Thesis
RI:  Research Internship

Wenn nicht anders angegeben, können die Themen in Deutsch oder Englisch bearbeitet werden.

Wenn Sie sich für die Bearbeitung eines der Themen interessieren, kontaktieren Sie bitte die angegebene Kotaktperson per Email. Bitte senden Sie Ihren Lebenslauf und eine Übersicht Ihrer bisherigen Studienleistungen mit.

Weitere Themen sind evtl. auf Nachfrage verfügbar. Kontaktieren Sie hier bitte direkt die wissenschafltichen Mitarbeiter*innen, die sich mit dem Themengebiet beschäftigen (siehe Homepage), das zu Ihren Interessen passt.

Dies gilt ebenso für Anfragen zur Betreuung externer Arbeiten. Bitte beachten Sie hierbei, dass diese nur von uns betreut werden, wenn das Thema in unser Arbeitsgebiet passt und für uns interessant ist.

BT:  Bachelorarbeit
MT: Masterarbeit
IP:   Ingenieurspraxis
RI:   Forschungspraxis


Type
(BT,MT,RI)		Topic
(with short description)		Contactpossible
start date		Time Topic Added

MT, RI, Projektpraktikum, Ingenieurspraxis, Forschungspraxis

Home Energy Management Systems Benchmarking Laboratory

Research method: Prototyping

Research question:

How can Home Energy Management Systems (EMS) be benchmarked in a Laboratory setup?

Possible approach:

  • Literature review on benchmarking of HEMS

  • Selection of exemplary HEMS publications, especially focusing methods like Reinforcement Learning that have public code accessible

  • Analysis of different scenarios and definition of requirements for Laboratory Setup for benchmarking HEMS

  • Implementation of the benchmarking setup in the laboratory using load emulators

  • Execution and Analysis of benchmarking process for exemplary HEMS publication methods


Sebastian Eichhorn
sebastian.eichhorn@tum.de

anytime05/2024
MT, RI, Projektpraktikum, Forschungspraxis

EnergyOS: Operating System Internal Resource and Data Management

Research method: Literature Review, Prototyping

Research question:

How can we store and retrieve data most efficiently?
Can we integrate caching and parallelization of requests?

Possible approach:

  • Literature review on data access and storage for time series applications, and data caching.

  • Creation and comparison of data management schemes
    • e.g. resource data stored using: (1) python data structures (local dictionaries and lists), (2) json files, (3) csv files, (4) common database like Postgres or MongoDB, (5) specialized time series database like InfluxDB.

  • Evaluation of schemes, their performance, how they scale (i.e. complexity in terms of time and storage).

  • Design of data caching procedure and parallelization of OS tasks.
  • Implementation of Resource and Data Management design in EnergyOS.

Your background/interests:

  • Energy Management Systems
  • Data Management / Databases
  • Programming experience helpful (python)

Background:

Current Energy Management Systems are monolithic systems with only one goal in mind and only a limited view of their environments. However, they often operate in parallel to other EMS systems that access the same resources, contain useful and relevant information for them, and/or have conflicting system objectives. EnergyOS is a connected EMS platform that allows multiple EMS apps to communicate, plan, and resolve these types of conflicts natively, by providing functionality for distributed resource management and control of EMS components. 

Ehimare Okoyomon
e.okoyomon@tum.de

Starting in WS 2024

03/2024

MT, RI, Projektpraktikum, Forschungspraxis

EnergyOS: Scheduling and OS-controlled Schedule Generation in a Multi-App EMS Platform

Research method: Literature Review, Prototyping

Research question:

What level of control should the EnergyOS have in creating and executing operation plan schedules for energy components?
How can this be used in practice and what are the advantages and challenges of such an approach?

Background:

Current Energy Management Systems are monolithic systems with only one goal in mind and only a limited view of their environments. However, they often operate in parallel to other EMS systems that access the same resources, contain useful and relevant information for them, and/or have conflicting system objectives. EnergyOS is a connected EMS platform that allows multiple EMS apps to communicate, plan, and resolve these types of conflicts natively, by providing functionality for distributed resource management and control of EMS components.

Possible approach:

  • Literature review of common EMS scheduling / optimization problems and state of the art methods for solving.

  • Implementation of one or more scheduling solutions in EnergyOS.
  • Creation of an interface to provide EnergyOS with a set of constraints, objectives, and data/resources.
  • Selection and implementation of use cases (EnergyOS apps) to demonstrate how OS-controlled scheduling works.

Your background/interests:

  • Energy Management Systems
  • Optimizations
  • Programming experience helpful (python)

Ehimare Okoyomon
e.okoyomon@tum.de

Currently not available03/2024
BT, MT, RI, Forschungspraxis

Development of Smart Grid Simulator (Project EDGE)

Research method: Prototyping

Research questions:

  • How can models of energy system components be containerized and deployed on a compute cluster?
  • How can performance, scalability, and reliability of this simulation infrastructure be measured?
  • How can basic EMS scenarios be simulated and analyzed using this infrastructure? 

Possible approach:

  • Setup local container development and cluster environment (Docker, Kubernetes, etc.)

  • Develop several energy system components as Docker containers exposing web-based interfaces (e.g., distribution grid, HEMS, HH energy demand simulator, solar PV simulator, battery charge controller, etc.)
  • Implement message-based communication between containers running on cluster
  • Measure performance in different scenarios  

Resources:

Christoph Goebel

christoph.goebel@tum.de

Sebastian Eichhorn

sebastian.eichhorn@tum.de

Elgin Kollnig 

elgin.kollnig@tum.de

flexible – please contact us!09/2023

BT, MT, RI, Forschungspraxis

Deep Learning based Estimation of Distribution Grid State

Research method: Prototyping

Research question:

  • How can state of distribution grids be estimated using deep learning?

Possible approach: 

  • Understand state of the art based on literature
  • Develop efficient Python code applying deep learning to estimate distribution grid states
  • Benchmark with state of the art methods

Christoph Goebel

christoph.goebel@tum.de

flexible – please contact me!

09/2023

BT, MT, RI, Forschungspraxis

Comparing Data Valuation Methods

Research method: prototyping/ simulation

Research question:

  • What is the value of a datapoint? How much does each datapoint contribute to model training?
  • How do different data valuation measures proposed in the literature compare to each other?

Possible approach: 

  • Understand state of the art based on literature
  • Implement methods in python
  • Compare on various datasets

Resources:

Jan Marco Ruiz de Vargas

janmarco.ruiz@tum.de 

flexible - please contact me!

09/2023

BT, MT, RI, Forschungspraxis

Extending Data Valuation to Regression Tasks

Research method: prototyping/ simulation

Research question:

  • What is the value of a datapoint? How much does each datapoint contribute to model training?
  • How can we extend data valuation measures proposed in the literature from classification tasks to regression tasks?

Possible approach: 

  • Understand state of the art based on literature
  • Think about how to extend data valuation to regression
  • Implement methods in python and compare on various datasets

Resources:

Jan Marco Ruiz de Vargas

janmarco.ruiz@tum.de 

 

flexible - please contact me!

09/2023

Supervisors see also → Processing for Theses (Bachelor/Master)

Betreuer siehe auch → Abwicklung von Abschlussarbeiten

  • Keine Stichwörter