Continuous-Time Autoregressive Processes for Modeling Electricity Prices and Renewable Energies

  • This thesis deals with stochastic models for electricity markets. The focus is on wholesale prices and renewable power generation. Continuous-time autoregressive (CAR) processes are frequently used in this context. We define two new types within the class of CAR processes and show their benefits in application to the electricity market. The first process extends CAR processes with regime switching mean-reversion rates by including a jump component. This is necessary because spikes are one of the most pronounced features of electricity prices. CAR processes with non-constant parameters are also considered in an innovative model for photovoltaic (PV) power generation. This model provides for the first time a pure statistical approach to map intraday variation of solar power infeed. The second newly defined stochastic process allows to include external information in a flexible way. This makes it possible to take many facets of renewable energy production into account when determining theThis thesis deals with stochastic models for electricity markets. The focus is on wholesale prices and renewable power generation. Continuous-time autoregressive (CAR) processes are frequently used in this context. We define two new types within the class of CAR processes and show their benefits in application to the electricity market. The first process extends CAR processes with regime switching mean-reversion rates by including a jump component. This is necessary because spikes are one of the most pronounced features of electricity prices. CAR processes with non-constant parameters are also considered in an innovative model for photovoltaic (PV) power generation. This model provides for the first time a pure statistical approach to map intraday variation of solar power infeed. The second newly defined stochastic process allows to include external information in a flexible way. This makes it possible to take many facets of renewable energy production into account when determining the electricity price. Since renewable energies have an increasing impact on electricity prices, models that can handle related information are becoming more and more important. All results are applied to the German electricity market. Implementations for the newly defined processes are provided in R and C++.show moreshow less

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Daniel Lingohr
URN:urn:nbn:de:bvb:384-opus4-578915
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/57891
Advisor:Gernot Müller
Type:Doctoral Thesis
Language:English
Year of first Publication:2019
Publishing Institution:Universität Augsburg
Granting Institution:Universität Augsburg, Mathematisch-Naturwissenschaftlich-Technische Fakultät
Date of final exam:2019/06/24
Release Date:2019/08/27
GND-Keyword:Energiemarkt; Erneuerbare Energien; Mathematische Modellierung; Autoregressiver Prozess
Institutes:Mathematisch-Naturwissenschaftlich-Technische Fakultät
Mathematisch-Naturwissenschaftlich-Technische Fakultät / Institut für Mathematik
Mathematisch-Naturwissenschaftlich-Technische Fakultät / Institut für Mathematik / Lehrstuhl für Rechnerorientierte Statistik und Datenanalyse
Dewey Decimal Classification:5 Naturwissenschaften und Mathematik / 51 Mathematik / 510 Mathematik
Licence (German):Deutsches Urheberrecht mit Print on Demand