Automated Deep Learning for load forecasting

Julie Keisler, Sandra Claudel, Gilles Cabriel, Margaux Brégère
Proceedings of the Third International Conference on Automated Machine Learning, PMLR 256:16/1-28, 2024.

Abstract

Accurate forecasting of electricity consumption is essential to ensure the performance and stability of the grid, especially as the use of renewable energy increases. Forecasting electricity is challenging because it depends on many external factors, such as weather and calendar variables. While regression-based models are currently effective, the emergence of new explanatory variables and the need to refine the temporality of the signals to be forecasted is encouraging the exploration of novel methodologies, in particular deep learning models. However, Deep Neural Networks (DNNs) struggle with this task due to the lack of data points and the different types of explanatory variables (e.g. integer, float, or categorical). In this paper, we explain why and how we used Automated Deep Learning (AutoDL) to find performing DNNs for load forecasting. We ended up creating an AutoDL framework called EnergyDragon by extending the DRAGON (\url{https://dragon-tutorial.readthedocs.io/en/latest/}) package and applying it to load forecasting. EnergyDragon automatically selects the features embedded in the DNN training in an innovative way and optimizes the architecture and the hyperparameters of the networks. We demonstrate on the French load signal that EnergyDragon can find original DNNs that outperform state-of-the-art load forecasting methods as well as other AutoDL approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v256-keisler24a, title = {Automated Deep Learning for load forecasting}, author = {Keisler, Julie and Claudel, Sandra and Cabriel, Gilles and Br\'eg\`ere, Margaux}, booktitle = {Proceedings of the Third International Conference on Automated Machine Learning}, pages = {16/1--28}, year = {2024}, editor = {Eggensperger, Katharina and Garnett, Roman and Vanschoren, Joaquin and Lindauer, Marius and Gardner, Jacob R.}, volume = {256}, series = {Proceedings of Machine Learning Research}, month = {09--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v256/main/assets/keisler24a/keisler24a.pdf}, url = {https://proceedings.mlr.press/v256/keisler24a.html}, abstract = {Accurate forecasting of electricity consumption is essential to ensure the performance and stability of the grid, especially as the use of renewable energy increases. Forecasting electricity is challenging because it depends on many external factors, such as weather and calendar variables. While regression-based models are currently effective, the emergence of new explanatory variables and the need to refine the temporality of the signals to be forecasted is encouraging the exploration of novel methodologies, in particular deep learning models. However, Deep Neural Networks (DNNs) struggle with this task due to the lack of data points and the different types of explanatory variables (e.g. integer, float, or categorical). In this paper, we explain why and how we used Automated Deep Learning (AutoDL) to find performing DNNs for load forecasting. We ended up creating an AutoDL framework called EnergyDragon by extending the DRAGON (\url{https://dragon-tutorial.readthedocs.io/en/latest/}) package and applying it to load forecasting. EnergyDragon automatically selects the features embedded in the DNN training in an innovative way and optimizes the architecture and the hyperparameters of the networks. We demonstrate on the French load signal that EnergyDragon can find original DNNs that outperform state-of-the-art load forecasting methods as well as other AutoDL approaches.} }
Endnote
%0 Conference Paper %T Automated Deep Learning for load forecasting %A Julie Keisler %A Sandra Claudel %A Gilles Cabriel %A Margaux Brégère %B Proceedings of the Third International Conference on Automated Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Katharina Eggensperger %E Roman Garnett %E Joaquin Vanschoren %E Marius Lindauer %E Jacob R. Gardner %F pmlr-v256-keisler24a %I PMLR %P 16/1--28 %U https://proceedings.mlr.press/v256/keisler24a.html %V 256 %X Accurate forecasting of electricity consumption is essential to ensure the performance and stability of the grid, especially as the use of renewable energy increases. Forecasting electricity is challenging because it depends on many external factors, such as weather and calendar variables. While regression-based models are currently effective, the emergence of new explanatory variables and the need to refine the temporality of the signals to be forecasted is encouraging the exploration of novel methodologies, in particular deep learning models. However, Deep Neural Networks (DNNs) struggle with this task due to the lack of data points and the different types of explanatory variables (e.g. integer, float, or categorical). In this paper, we explain why and how we used Automated Deep Learning (AutoDL) to find performing DNNs for load forecasting. We ended up creating an AutoDL framework called EnergyDragon by extending the DRAGON (\url{https://dragon-tutorial.readthedocs.io/en/latest/}) package and applying it to load forecasting. EnergyDragon automatically selects the features embedded in the DNN training in an innovative way and optimizes the architecture and the hyperparameters of the networks. We demonstrate on the French load signal that EnergyDragon can find original DNNs that outperform state-of-the-art load forecasting methods as well as other AutoDL approaches.
APA
Keisler, J., Claudel, S., Cabriel, G. & Brégère, M.. (2024). Automated Deep Learning for load forecasting. Proceedings of the Third International Conference on Automated Machine Learning, in Proceedings of Machine Learning Research 256:16/1-28 Available from https://proceedings.mlr.press/v256/keisler24a.html.

Related Material