Tim Janke

M.Sc. Tim Janke

Probabilistic price forecasting for electricity markets

+49 (0) 6151 16-21714
fax +49 (0) 6151 16-21712

S3|10 303
Landgraf-Georg-Str. 4
64283 Darmstadt

Research Interest

General research interests:

  • Machine learning and data analysis in the energy domain
  • Uncertainty quantification
  • Probabilistic forecasting
  • Energy market design & regulation

Current project: probabilistic price forecasting for electricity markets

In the course of the Energiewende the share of renewable energy sources (RES) in the total electricity generation has steadily increased. One main characteristic of RES is their dependence on the given supply, i.e. solar radiation or wind speed, which renders the expected production from these sources volatile and uncertain. This motivates the efforts currently undertaken to increase the ability of the demand side to react flexible to the increasingly volatile generation. Furthermore, the markets for energy and power gained in importance. Market prices play the key role for the effective and efficient coordination of the volatile and uncertain generation from RES, the thermal generation, and the flexible share of the demand. Operators of flexibility options, such as storages, industrial processes, gas turbines, or heat pumps, must decide at all times on bid prices and quantities as well as on the market at which they place their offer under an uncertain future market price. Hence, the operators face a complex stochastic optimization problem with the market price as the key parameter.

Therefore, the goal of the project is to develop and validate methods and algorithms for the reliable probabilistic forecasting of electricity prices for several markets. A probabilistic forecast, i.e. a forecast of a probability distribution for each point in time instead of just a single, most likely value, enables the application of stochastic optimization methods because it allows the incorporation the of uncertainty of the prediction. This is especially relevant in times of high volatility or extreme prices events. The developed methods should help to encourage and facilitate the active participation of small and medium sized suppliers, prosumers, and consumers in modern energy markets.

The project is done in cooperation with the Entega AG and funded by the TU Darmstadt Pioneer Fund.

            

Open theses

Unfortunately, there is nothing available in the moment.

Short Bio

  • Since 2017: PhD student at EINS

  • 2013 – 2017: M.Sc. Business Administration/Industrial Engineering at TU Darmstadt and University of Bergamo

  • 2008 – 2013: B.Sc. Business Administration/Industrial Engineering at TU Darmstadt

Publications

Probabilistic multivariate electricity price forecasting using implicit generative ensemble post-processing

Tim Janke ; Florian Steinke :
Probabilistic multivariate electricity price forecasting using implicit generative ensemble post-processing.
In: 16th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS 2020), virtual Conference, 18.-21.08., ISBN 9781728128238,
DOI: 10.1109/PMAPS47429.2020.9183687,
[Conference Contribution] [TUDBiblio][BibTeX], (2020)

Evaluation of Day-Ahead Electricity Price Predictions with Multi-Stage Stochastic Programs

Mario Beykirch ; Tim Janke ; Florian Steinke :
Evaluation of Day-Ahead Electricity Price Predictions with Multi-Stage Stochastic Programs.
In: 8th International Ruhr Energy Conference (INREC 2019), Essen, Germany, 25.-26.09.2019,
[Conference Contribution] [TUDBiblio][BibTeX], (2019)

Bayesian Inference with MILP Dispatch Models for the Probabilistic Prediction of Power Plant Dispatch

Mario Beykirch ; Tim Janke ; Florian Steinke :
Bayesian Inference with MILP Dispatch Models for the Probabilistic Prediction of Power Plant Dispatch.
In: 16th International Conference on the European Energy Market (EEM), Ljubljana, Slovenia, 18.09.2019 - 20.09.2019,
DOI: 10.1109/EEM.2019.8916530,
[Conference Contribution] [TUDBiblio][BibTeX], (2019)

Learning Dispatch Parameters of Thermal Power Plants from Observations

Mario Beykirch ; Tim Janke ; Florian Steinke :
Learning Dispatch Parameters of Thermal Power Plants from Observations.
In: 8th IEEE PES Innovative Smart Grid Technologies Conference Europe, Sarajevo, Bosnia-Herzegovina, 21.-25.10.2018,
DOI: 10.1109/ISGTEurope.2018.8571825,
[Conference Contribution] [TUDBiblio][BibTeX], (2018)

Incentivizing the adoption of local flexibility options: A quantitative case study

Tim Janke ; Bastian Brindley ; Tobias Rodemann ; Florian Steinke :
Incentivizing the adoption of local flexibility options: A quantitative case study.
In: 15th International Conference on the European Energy Market (EEM'18), Lodz, Poland, 27.-29. June 2018,
DOI: 10.1109/EEM.2018.8469854,
[Conference Contribution] [TUDBiblio][BibTeX], (2018)