Time Series Electricity Price Forecast on the German Day-ahead Market

Detalhes bibliográficos
Autor(a) principal: Hillmann, Steffen Maximilian
Data de Publicação: 2022
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/140860
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
id RCAP_ed88112e392c83af7433b0de49abb3e8
oai_identifier_str oai:run.unl.pt:10362/140860
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Time Series Electricity Price Forecast on the German Day-ahead MarketShort-term electricity price forecastingMachine learningNeural networkDeep learningGerman electricity marketSDG 10 - Reduced Inequalities: Reducing income and other inequalities, within and between countriesSDG 12 - Responsible Consumption and Production: Reversing current consumption trends and promoting a more sustainable futureSGD 13 - Climate Action: Regulating and reducing emissions and promoting renewable energyDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business AnalyticsDue to the liberalization of the European energy market, electricity prices are now determined based on contracts on regulated markets like any other commodity. They are mainly driven by supply and demand forces. In a rather complex and competitive market where prices are characterized by high volatility and depend on various factors, an accurate forecast of the electricity spot price is a significant source of risk for many participants and, therefore, an essential aspect of effective risk management. The increasing dependence on renewable energy sources and their dependence on weather contribute to the growing importance of electricity price forecasting (EPF). Accurate forecasts provide every market participant with important information for planning bidding strategies to minimize risks and maximize profits and utilities. Extensive research has therefore been conducted in recent decades to develop methods for short-term price forecasting. This research aims to conduct a comparative study to investigate the forecasting performance by using and comparing different time series forecasting methods, including traditional statistical, machine learning, and deep learning models, for the German electricity market. Deep-learning models are gaining interest among researchers nowadays and are expected to perform better than models based on static methods. The models are used to produce a one-step forecast with hourly data of the German electricity market for the whole year 2020. Thus the thesis aims to answer the following research questions: (1) to what extent can deep learning models handle non-stationary time series better than statistical time series methods and machine learning models, and how reliable are the day-a-head electricity price forecast in practice? and (2) does the production of renewable energies for individual hours contain helpful predictive information for EPF that helps market participants to improve their bidding strategies and control risk? Final analyses included data from hourly EPEX Spot electricity prices for Germany from January 2016 until December 2020, as well as historical load and generation data from ENTSO-E and historical weather data from OpenWeatherMap. The empirical out-of-sample results show that deep learning models perform better than statistical and machine learning models. Especially the multivariate GRU outperformed other deep learning models not only in validation accuracy and prediction consistency, due to its memory about the previous time steps.Damásio, Bruno Miguel PintoRUNHillmann, Steffen Maximilian2022-06-27T15:09:32Z2022-06-072022-06-07T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/140860TID:203028538enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:18:04Zoai:run.unl.pt:10362/140860Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:49:48.815251Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Time Series Electricity Price Forecast on the German Day-ahead Market
title Time Series Electricity Price Forecast on the German Day-ahead Market
spellingShingle Time Series Electricity Price Forecast on the German Day-ahead Market
Hillmann, Steffen Maximilian
Short-term electricity price forecasting
Machine learning
Neural network
Deep learning
German electricity market
SDG 10 - Reduced Inequalities: Reducing income and other inequalities, within and between countries
SDG 12 - Responsible Consumption and Production: Reversing current consumption trends and promoting a more sustainable future
SGD 13 - Climate Action: Regulating and reducing emissions and promoting renewable energy
title_short Time Series Electricity Price Forecast on the German Day-ahead Market
title_full Time Series Electricity Price Forecast on the German Day-ahead Market
title_fullStr Time Series Electricity Price Forecast on the German Day-ahead Market
title_full_unstemmed Time Series Electricity Price Forecast on the German Day-ahead Market
title_sort Time Series Electricity Price Forecast on the German Day-ahead Market
author Hillmann, Steffen Maximilian
author_facet Hillmann, Steffen Maximilian
author_role author
dc.contributor.none.fl_str_mv Damásio, Bruno Miguel Pinto
RUN
dc.contributor.author.fl_str_mv Hillmann, Steffen Maximilian
dc.subject.por.fl_str_mv Short-term electricity price forecasting
Machine learning
Neural network
Deep learning
German electricity market
SDG 10 - Reduced Inequalities: Reducing income and other inequalities, within and between countries
SDG 12 - Responsible Consumption and Production: Reversing current consumption trends and promoting a more sustainable future
SGD 13 - Climate Action: Regulating and reducing emissions and promoting renewable energy
topic Short-term electricity price forecasting
Machine learning
Neural network
Deep learning
German electricity market
SDG 10 - Reduced Inequalities: Reducing income and other inequalities, within and between countries
SDG 12 - Responsible Consumption and Production: Reversing current consumption trends and promoting a more sustainable future
SGD 13 - Climate Action: Regulating and reducing emissions and promoting renewable energy
description Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
publishDate 2022
dc.date.none.fl_str_mv 2022-06-27T15:09:32Z
2022-06-07
2022-06-07T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/140860
TID:203028538
url http://hdl.handle.net/10362/140860
identifier_str_mv TID:203028538
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138095878111232

Registros relacionados