Filling missing values for AI-based (load) forecasts within the InterFlex micro grid demo in Simris, Sweden

Thumbnail Image

Files

CIRED 2019 - 184.pdf (375.29 KB)

Paper number

184

Working Group Number

Conference name

CIRED 2019

Conference date

3-6 June 2019

Conference location

Madrid, Spain

Peer-reviewed

Yes

Short title

Convener

Authors

Pohlmann, Roxana, RWTH Aachen, Germany
Wilms, Henning, RWTH Aachen, Germany
Cupelli, Marco, EON Energy Research Center - RWTH Aachen, Germany
Elgezua Fernandez, Inko, E.ON, Germany
Monti, Antonello, EON Energy Research Center - RWTH Aachen, Germany

Abstract

                                                Missing data impairs the performance of most neural networks with a particularly strong effect on time series prediction networks. Imputation addresses this issue and by replacing missing values with substitute values. The choice of a suitable imputation method requires fundamental knowledge of the dataset.                   Autoencoders (AE) have been widely applied in representation learning and feature extraction. In this paper we use a stacked denoising overcomplete autoencoder for imputation in multi-variate time series. We assess the model’s feature reproduction capability and compare its effect to simple mean imputation on a open source data set. Moreover, we assess the imputation’s influence on a recurrent neural network’s short-term load forecasting results and show that our proposed autoencoder model yields better results in feature imputation and significantly improves the forecasting accuracy for low and high fractions of missing data.

Table of content

Keywords

Publisher

AIM

Date

2019-06-03

Published in

CIRED 2019 Conference

Permanent link to this record

https://cired-repository.org/handle/20.500.12455/593
http://dx.doi.org/10.34890/817

ISSN

2032-9644

ISBN

978-2-9602415-0-1