Filling missing values for AI-based (load) forecasts within the InterFlex micro grid demo in Simris, Sweden
Loading...
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
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
Permanent link to this record
https://cired-repository.org/handle/20.500.12455/593
http://dx.doi.org/10.34890/817
http://dx.doi.org/10.34890/817
ISSN
2032-9644
ISBN
978-2-9602415-0-1