Zur Kurzanzeige

dc.contributor.author
Naumzik, Christof
dc.contributor.author
Feuerriegel, Stefan
dc.date.accessioned
2021-01-25T20:16:45Z
dc.date.available
2020-06-23T10:07:26Z
dc.date.available
2020-06-24T08:06:59Z
dc.date.available
2021-01-25T20:16:45Z
dc.date.issued
2021
dc.identifier.issn
1750-6220
dc.identifier.other
10.1108/IJESM-01-2020-0001
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/421909
dc.description.abstract
Purpose Trading on electricity markets occurs such that the price settlement takes place before delivery, often day-ahead. In practice, these prices are highly volatile as they largely depend upon a range of variables such as electricity demand and the feed-in from renewable energy sources. Hence, the purpose of this paper is to provide accurate forecasts.. Design/methodology/approach This paper aims at comparing different predictors stemming from supply-side (solar and wind power generation), demand-side, fuel-related and economic influences. For this reason, this paper implements a broad range of non-linear models from machine learning and draw upon the information-fusion-based sensitivity analysis. Findings This study disentangles the respective relevance of each predictor. This study shows that external predictors altogether decrease root mean squared errors by up to 21.96%. A Diebold-Mariano test statistically proves that the forecasting accuracy of the proposed machine learning models is superior. Research limitations/implications The performance gain from including more predictors might be larger than from a better model. Future research should place attention on expanding the data basis in electricity price forecasting. Practical implications When developing pricing models, practitioners can achieve reasonable performance with a simple model (e.g. seasonal-autoregressive moving-average) that is built upon a wide range of predictors. Originality/value The benefit of adding further predictors has only recently received traction; however, little is known about how the individual variables contribute to improving forecasts in machine learning.
en_US
dc.language.iso
en
en_US
dc.publisher
Emerald
en_US
dc.subject
Artificial intelligence
en_US
dc.subject
Forecasting
en_US
dc.subject
Neural networks
en_US
dc.subject
Electricity
en_US
dc.title
Forecasting electricity prices with machine learning: Predictor sensitivity
en_US
dc.type
Journal Article
dc.date.published
2020-09-21
ethz.journal.title
International Journal of Energy Sector Management
ethz.journal.volume
15
en_US
ethz.journal.issue
1
en_US
ethz.pages.start
58
en_US
ethz.pages.end
80
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Bingley
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan (ehemalig) / Feuerriegel, Stefan (former)
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan (ehemalig) / Feuerriegel, Stefan (former)
en_US
ethz.date.deposited
2020-06-23T10:07:36Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-01-25T20:17:04Z
ethz.rosetta.lastUpdated
2022-03-29T04:58:14Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Forecasting%20electricity%20prices%20with%20machine%20learning:%20Predictor%20sensitivity&rft.jtitle=International%20Journal%20of%20Energy%20Sector%20Management&rft.date=2021&rft.volume=15&rft.issue=1&rft.spage=58&rft.epage=80&rft.issn=1750-6220&rft.au=Naumzik,%20Christof&Feuerriegel,%20Stefan&rft.genre=article&rft_id=info:doi/10.1108/IJESM-01-2020-0001&
 Printexemplar via ETH-Bibliothek suchen

Dateien zu diesem Eintrag

DateienGrößeFormatIm Viewer öffnen

Zu diesem Eintrag gibt es keine Dateien.

Publikationstyp

Zur Kurzanzeige