Probabilistic wind power forecasting combining deep learning architectures

Eric Lacoa Arends, Simon J. Watson, Sukanta Basu, Bedassa Cheneka

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

71 Downloads (Pure)

Abstract

A series of probabilistic models were bench-marked during the European Energy Markets forecasting Competition 2020 to assess their relative accuracy in predicting aggregated Swedish wind power generation using as input historic weather forecasts from a numerical weather prediction model. In this paper, we report the results of one of these models which uses a deep learning approach integrating two architectures: (a) Convolutional Neural Network (CNN) LeNet-5 based architectrure; (b) Multi-Layer Perceptron (MLP) architecture -with two hidden layers-. These are concatenated into the Smooth Pinball Neural Network (SPNN) framework for quantile regression. Hyperparameters were optimised to produce the best model for every region. When tuned, the re-forecasts from the model performed favorably compared to other machine learning approaches and showed significant improvement on the original competition results, though failed to fully capture spatial patterns in certain cases when compared to other methods.

Original languageEnglish
Title of host publication2020 17th International Conference on the European Energy Market, EEM 2020
PublisherIEEE
Number of pages6
ISBN (Electronic)9781728169194
DOIs
Publication statusPublished - 2020
Event17th International Conference on the European Energy Market, EEM 2020 - Stockholm, Sweden
Duration: 16 Sept 202018 Sept 2020

Publication series

NameInternational Conference on the European Energy Market, EEM
Volume2020-September
ISSN (Print)2165-4077
ISSN (Electronic)2165-4093

Conference

Conference17th International Conference on the European Energy Market, EEM 2020
Country/TerritorySweden
CityStockholm
Period16/09/2018/09/20

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • convolutional neural network
  • multilayer perceptron
  • numerical weather prediction
  • smooth pinball neural network
  • wind power forecasting

Fingerprint

Dive into the research topics of 'Probabilistic wind power forecasting combining deep learning architectures'. Together they form a unique fingerprint.

Cite this