Bachelor's and Master's Theses or Research Internship / Bachelor- und Masterarbeiten oder Forschungspraxis

Probabilistic PV / Load Forecasts

Research method: Protoytping, Modelling

Research questions: 

• How can we quantify the uncertainty via probabilistic forecasts of, e.g., PV production and load?
• What constraints do we face on the algorithm side if we want to have embedded forecasts?
• How can we use conformal prediction to go from point forecasts to probabilistic forecasts?

Possible approach: 

• Literature Research of State of the Art of PV or Load Forecasting
• Find Research Gap 
• Implement own ideas
• Validate Results e.g. with PV on institute's roof

Suggested Readings:

• A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES) | Journal of Renewable and Sustainable Energy | AIP Publishing
• Core Concepts and Methods in Load Forecasting: With Applications in Distribution Networks | SpringerLink
• Energy Forecasting: A Review and Outlook: pierrepinson.com/wp-content/uploads/2020/10/Hongetal2020.pdf

Concepts and Tools:

• Python/Julia: pandas, DataFrames.jl
• Time Series Forecasting and Machine Learning: sktime, functime, Darts, scikit learn, MAPIE

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)

Ehimare Okoyomon
e.okoyomon@tum.de

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?

• 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

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:

• Docker
• Kubernetes
• lemlab
• RabbitMQ

Christoph Goebel

christoph.goebel@tum.de

Sebastian Eichhorn

sebastian.eichhorn@tum.de

Elgin Kollnig 

elgin.kollnig@tum.de

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

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:

• What is your data worth? - Data Shapley Video

• Data Valuation without training of a model - Research Paper

Jan Marco Ruiz de Vargas

janmarco.ruiz@tum.de 

Extending Data Valuation to continuous predictions

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 discrete predictions to continuous predictions?

Possible approach: 

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

Resources:

• What is your data worth? - Data Shapley Video

• Data Valuation without training of a model - Research Paper

Jan Marco Ruiz de Vargas

janmarco.ruiz@tum.de