Dealing with uncertainty: An empirical study on the relevance of renewable energy forecasting methods

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Contributors

  • Robert Ulbricht - , Robotron Datenbank-Software GmbH (Author)
  • Anna Thoß - , Dresden University of Applied Sciences (HTW) (Author)
  • Hilko Donker - , Robotron Datenbank-Software GmbH (Author)
  • Gunter Gräfe - , Dresden University of Applied Sciences (HTW) (Author)
  • Wolfgang Lehner - , Chair of Databases (Author)

Abstract

The increasing share of fluctuating renewable energy sources on the world-wide energy production leads to a rising public interest in dedicated forecasting methods. As different scientific communities are dedicated to that topic, many solutions are proposed but not all are suited for users from utility companies. We describe an empirical approach to analyze the scientific relevance of renewable energy forecasting methods in literature. Then, we conduct a survey amongst forecasting software providers and users from the energy domain and compare the outcomes of both studies.

Details

Original languageEnglish
Title of host publicationData Analytics for Renewable Energy Integration
EditorsZeyar Aung, Stuart Madnick, Oliver Kramer, Wei Lee Woon
PublisherSpringer, Berlin [u. a.]
Pages54-66
Number of pages13
ISBN (print)9783319509464
Publication statusPublished - 2017
Peer-reviewedYes

Publication series

SeriesLecture Notes in Computer Science, Volume 10097
ISSN0302-9743

Conference

Title4th International Workshop on Data Analytics for Renewable Energy Integration, DARE 2016
Duration23 September 2016
CityRiva del Garda
CountryItaly

External IDs

ORCID /0000-0001-8107-2775/work/142253529

Keywords

Sustainable Development Goals

Keywords

  • Machine learning, Practical relevance, Renewable energy forecasting