Projektpraktikum
4 SWS
Module Description: https://campus.tum.de/tumonline/pl/ui/$ctx;design=pl;header=max;lang=DE/wbLv.wbShowLVDetail?pStpSpNr=950729670

SS 2024 Nr: 0000002995

Description

  • Participants of the course gain hands-on experience in research projects related to Energy Management.
  • Possible topics include but not limited to:
    • EMS and distributed energy systems development
    • Grid simulation
    • Energy system optimizations
    • Energy forecasting
    • Energy Data curation and analytics
  • Both individual and group work is possible.
  • A kickoff session will be conducted to introduce the course and topics. Afterwards, students can apply for topics by sending the top three topics and the current transcript of records to e.okoyomon@tum.de.
  • Regular follow-up meetings with the participants and supervisor are held to aid the participants with the seminar tasks.
  • All presentations and reports in English. Advisor↔participant communication language may vary.

Deliverables, important dates, and current topics listed below.

Deliverables

At the end of the semester, participants will have to submit:

  • a scientific paper (~7 pages per student, submitted as the seminar report).
  • a conference-style final presentation, including demo, or proof of concept.

Both of these must be submitted on time and any late work may not be accepted.

Important Dates (Summer Semester 2024)


DateTimePlace
Registration Period28.02.24 - 03.05.24
TUMOnline
Kickoff Meeting17.04.244:30pm - 5:30pmroom N3815
Topic preferences submission19.04.24.midnightemail
Topic allocation24.04.247pmemail
Final Presentation22.07.242:30pm - 4:30pmroom N3815
Final Report due29.07.24midnightmoodle


Topics

If you have any more questions about a topic, please contact the advisor/contact directly. For topic preference submissions, contact e.okoyomon@tum.de.


AcronymTopic descriptionRequired skillsNumber of StudentsContact

OET_FC

AI energy short-term forecasting for energy trading in real-world scenarios

Forecasting_-_project_OET.pdf

Research method: Prototyping

Research questions:

  • Which features and optimization techniques are important in energy forecasting of individual power plants and consumers
  • How do Neural forecasting models (ANNs, RNNs, …) compare against Machine learning models in energy forecasting (load, solar or both)?
  • How to improve the forecast accuracy of special dates like holidays in load forecasting?
  • What is the impact of forecast accuracy on the energy trading earnings of customers in real-world scenarios?

Possible approach:

  • Get access to historical and live consumption and production energy data of real PV power plants and consumers
  • Develop new forecasting models and compare the performance with the already-existing models
  • Deploy the model to the energy trading platform - Observe and measure accuracy of forecasts and changes in trading earnings in different scenarios

Resources:

Expected Output:

  • Forecasting models producing forecasts for PV, load or both
  • Forecasting models ready-to-be used for live energy trading

 

  • Programming skills in Python
  • Basic skills in Machine Learning
  • Interest in Forecasting in real-life scenarios

1-3

Christoph Goebel

christoph.goebel@tum.de

(collaboration with Otter Energy Trading

hello@otter-energy-trading.io)

 

EDGE_DEV

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:

 

  • Good programming skills in Python and/or Julia
  • Interest in DevOps, e.g., containerization, cluster-based provision of services, etc.

3-4

Christoph Goebel

christoph.goebel@tum.de

Sebastian Eichhorn

sebastian.eichhorn@tum.de

Elgin Kollnig 

elgin.kollnig@tum.de

EDL_DEV

Build a Digital Platform for Energy Data and Code Sharing (Project: Energy Data Lab)

Learn more about the project on our website!

Research method: Prototyping

Research questions:

  • How can we set up a web platform to facilitate research data and code exchange?
  • What use case can we find to test the platform?
  • What features are required to enable the use case?

Possible approach:

  • (1) Web-Development
  • (2) Data Curation
  • (3) Database and general IT infrastructure

Resources:

  • Passion for programming

2-4

Annika Schneider

annikakristina.schneider@tum.de 

EOS_EV_MANAGEMENT

Electric Vehicle Fleet Management using EnergyOS

Research method: Prototyping

Research questions:

  • What are the impacts of the different EV charging and DSO control strategies on the distribution network?
  • How can we use EnergyOS to emulate this through control of a (large-scale) fleet of electric vehicles?

Possible approach:

  • Review the state of the art in electric vehicle fleet management in smart grids
  • Summarize the most relevant different EV charging and DSO control strategies from the literature
  • Using EnergyOS, implement a simulation to evaluate the different EV control combinations and present findings in the form of plots, tables, and a demo.
  • Come up with new ways to do Peer-to-peer control of EVs using EnergyOS resource sharing. 
  • To simulate with EnergyOS could involve:
    • Implement EnergyOS apps to represent households of different, realistic configurations (electric vehicle, load, with or without PV, ev availability, etc) and the different charging strategies
    • Implement EnergyOS app(s) for the different DSO charging strategies
    • Connect the apps via EnergyOS to share information and execute control 

Resources:

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.

image-2024-2-19_10-54-10.png


  • Programming skills in python
  • Interest in Energy Management Systems and Distribution Grids

2-4

Ehimare Okoyomon

e.okoyomon@tum.de


 



 

Template

Template (Copy line and adapt)

Research method: literature review, modelling, experimental, ...

Research question: 

Possible approach: 



 

  • Keine Stichwörter