Date
2022-10-30Subject
620 Engineering WindenergieErneuerbare EnergienFotovoltaikDeep learningCodierungWettervorhersageElektrizitätsversorgungsnetzMetadata
Show full item record
Aufsatz
Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts
Abstract
Integrating new renewable energy resources requires robust and reliable forecasts to ensure a stable electrical grid and avoid blackouts. Sophisticated representation learning techniques, such as autoencoders, play an essential role, as they allow for the extraction of latent features to forecast the expected generated wind and photovoltaic power for the next seconds up to days. Thereby, autoencoders reduce the required training time and the time spent in manual feature engineering and often improve the forecast error. However, most current renewable energy forecasting research on autoencoders focuses on smaller forecast horizons for the following seconds and hours based on meteorological measurements. At the same time, larger forecast horizons, such as day-ahead power forecasts based on numerical weather predictions, are crucial for planning loads and demands within the electrical grid to prevent power failures. There is little evidence on the ability of autoencoders and their respective forecasting models to improve through multi-task learning and time series autoencoders for day-ahead power forecasts. We can close these gaps by proposing a multi-task learning autoencoder based on the recently introduced temporal convolution network. This approach reduces the number of trainable parameters by 38 for photovoltaic data and 202 for wind data while having the best reconstruction error compared to nine other representation learning techniques. At the same time, this model decreases the day-ahead forecast error up to 18.3% for photovoltaic parks and 1.5% for wind parks. We round off these results by analyzing the influences of the latent size and the number of layers to fine-tune the encoder for wind and photovoltaic power forecasts.
Citation
In: Energies Volume 15 / Issue 21 (2022-10-30) eissn:1996-1073Sponsorship
Gefördert durch den Publikationsfonds der Universität KasselCitation
@article{doi:10.17170/kobra-202211147108,
author={Schreiber, Jens and Sick, Bernhard},
title={Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts},
journal={Energies},
year={2022}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2022$n2022 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/14248 3000 Schreiber, Jens 3010 Sick, Bernhard 4000 Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts / Schreiber, Jens 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/14248=x R 4204 \$dAufsatz 4170 5550 {{Windenergie}} 5550 {{Erneuerbare Energien}} 5550 {{Fotovoltaik}} 5550 {{Deep learning}} 5550 {{Codierung}} 5550 {{Wettervorhersage}} 5550 {{Elektrizitätsversorgungsnetz}} 7136 ##0##http://hdl.handle.net/123456789/14248
2022-11-14T13:10:26Z 2022-11-14T13:10:26Z 2022-10-30 doi:10.17170/kobra-202211147108 http://hdl.handle.net/123456789/14248 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ transfer learning wind power photovolatic power autoencoders deep learning time series 620 Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts Aufsatz Integrating new renewable energy resources requires robust and reliable forecasts to ensure a stable electrical grid and avoid blackouts. Sophisticated representation learning techniques, such as autoencoders, play an essential role, as they allow for the extraction of latent features to forecast the expected generated wind and photovoltaic power for the next seconds up to days. Thereby, autoencoders reduce the required training time and the time spent in manual feature engineering and often improve the forecast error. However, most current renewable energy forecasting research on autoencoders focuses on smaller forecast horizons for the following seconds and hours based on meteorological measurements. At the same time, larger forecast horizons, such as day-ahead power forecasts based on numerical weather predictions, are crucial for planning loads and demands within the electrical grid to prevent power failures. There is little evidence on the ability of autoencoders and their respective forecasting models to improve through multi-task learning and time series autoencoders for day-ahead power forecasts. We can close these gaps by proposing a multi-task learning autoencoder based on the recently introduced temporal convolution network. This approach reduces the number of trainable parameters by 38 for photovoltaic data and 202 for wind data while having the best reconstruction error compared to nine other representation learning techniques. At the same time, this model decreases the day-ahead forecast error up to 18.3% for photovoltaic parks and 1.5% for wind parks. We round off these results by analyzing the influences of the latent size and the number of layers to fine-tune the encoder for wind and photovoltaic power forecasts. open access Schreiber, Jens Sick, Bernhard doi:10.3390/en15218062 Windenergie Erneuerbare Energien Fotovoltaik Deep learning Codierung Wettervorhersage Elektrizitätsversorgungsnetz publishedVersion eissn:1996-1073 Issue 21 Energies Volume 15 false 8062
The following license files are associated with this item: