Data Science in Energy and Environment

Modul: Data Science in Energy and Environment (6 Credits)
Name im Diploma Supplement	Data Science in Energy and Environment
Verantwortlich	Prof. Dr. Florian Ziel
Voraussetzungen	Siehe Prüfungsordnung.
Workload	180 Stunden studentischer Workload gesamt, davon: Präsenzzeit: 30 Stunden Vorbereitung, Nachbereitung: 110 Stunden Prüfungsvorbereitung: 40 Stunden
Dauer	Das Modul erstreckt sich über 1 Semester.
Qualifikationsziele	The students have an advanced understanding of forecasting concepts and techniques applied in energy markets will use statistical software R to fit estimation and forecasting algorithms to real world data can visualize and interpret obtained results
Prüfungsmodalitäten	Weighted average of a group R-project and a presentation (usually about 20 minutes). In Bezug auf das Niveau der zu erbringenden Leistung erfolgt eine Binnendifferenzierung nach Bachelor- bzw. Masterstudiengang. Die Prüfung in diesem Modul darf nicht abgelegt werden, wenn "Advanced Forecasting in Energy Markets" bereits bestanden ist.
Verwendung in Studiengängen	BWL Bachelor > Vertiefungsstudium > Seminarbereich > 4.-6. FS, Wahlpflicht BWL EaF Master > Seminarbereich > 2.-3. FS, Wahlpflicht ECMX Master > Wahlpflichtbereich > ME5 Economics > 1.-3. FS, Wahlpflicht MuU Master > Seminarbereich Märkte und Unternehmen > 2.-3. FS, Wahlpflicht VWL Bachelor > Vertiefungsstudium > Wahlpflichtbereich > Vertiefungsbereich Zusatzseminar > 4.-6. FS, Wahlpflicht VWL Master > Seminarbereich > 2.-3. FS, Wahlpflicht
Bestandteile	Seminar Data Science in Energy and Environment (6 Credits)
Modul: Data Science in Energy and Environment (WIWI‑M0796)

Seminar: Data Science in Energy and Environment (6 Credits)
Name im Diploma Supplement	Advanced Forecasting in Energy Markets
Anbieter	Lehrstuhl für Data Science in Energy and Environment
Lehrperson	Prof. Dr. Florian Ziel
Semesterwochenstunden	2	Sprache	englisch
Turnus	unregelmäßig	maximale Hörerschaft	20
empfohlenes Vorwissen Good knowledge of linear models and autoregressive processes. Experienced R knowledge. Sucessful participation in Econometrics of Electricity Markets is very helpful.
Abstract The purpose of this seminar is to provide an advanced understanding of modeling and forecasting methods in energy markets, esp. concerning probabilistic forecasting. The students apply sophisticated forecasting methods to real data (e.g. electricity or natural gas prices, electricity load, wind and solar power production) using the statistical Software R. They write a report and present their findings. The focus of the seminar is placed especially on probabilistic forecasting with different applications in e.g. electricity price and electricity load or wind and solar power production forecasting. A particular attention is given to regression-based modeling methods for electricity market data.
Lehrinhalte Introduction to selected statistical/machine learning/forecasting concepts and techniques Evaluation frameworks Applications to problems in energy (markets) or the environment.
Literaturangaben Hong, T., Pinson, P., Fan, S., Zareipour, H., Troccoli, A., & Hyndman, R. J. (2016). Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond. Nowotarski, J., & Weron, R. (2017). Recent advances in electricity price forecasting: A review of probabilistic forecasting. Renewable and Sustainable Energy Reviews. Petropoulos, F., Apiletti, D., Assimakopoulos, V., Babai, M. Z., Barrow, D. K., Taieb, S. B., ... & Ziel, F. (2022). Forecasting: theory and practice. International Journal of Forecasting, 38(3), 705-871.
didaktisches Konzept In the first few weeks the students learn the concepts of probabilistic forecasting in classes. Afterwards they apply the methods to energy market data using R, write a report and present their results.
Seminar: Data Science in Energy and Environment (WIWI‑C1106)