Next Article in Journal
Ulvan, a Polysaccharide from Macroalga Ulva sp.: A Review of Chemistry, Biological Activities and Potential for Food and Biomedical Applications
Next Article in Special Issue
The Impact of Data Filtration on the Accuracy of Multiple Time-Domain Forecasting for Photovoltaic Power Plants Generation
Previous Article in Journal
Multiscale Analysis of the Influence of Steel Fiber Reinforcement on the Shear Strength of Post-Tensioned Dry Joints
Previous Article in Special Issue
Analysis of the Impact of Residential Property and Equipment on Building Energy Efficiency and Consumption—A Data Mining Approach
Article

Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting

1
Data Science and Big Data Lab, Pablo de Olavide University, ES-41013 Seville, Spain
2
Computer Engineer Department, Universidad Americana de Paraguay, Asunción 1029, Paraguay
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Appl. Sci. 2020, 10(16), 5487; https://doi.org/10.3390/app10165487
Received: 1 July 2020 / Revised: 30 July 2020 / Accepted: 5 August 2020 / Published: 7 August 2020
The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these would allow allocating only the resources needed for the production of the right amount of energy required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can be used to this aim. Our proposal uses a genetic algorithm in order to find a sub-optimal set of hyper-parameters for configuring a deep neural network, which can then be used for obtaining the forecasting. Such a strategy is justified by the observation that the performances achieved by deep neural networks are strongly dependent on the right setting of the hyper-parameters, and genetic algorithms have shown excellent search capabilities in huge search spaces. Moreover, we base our proposal on a distributed computing platform, which allows its use on a large time-series. In order to assess the performances of our approach, we have applied it to a large dataset, related to the electric energy consumption registered in Spain over almost 10 years. Experimental results confirm the validity of our proposal since it outperforms all other forecasting techniques to which it has been compared. View Full-Text
Keywords: time-series forecasting; deep learning; evolutionary computation; neuroevolution time-series forecasting; deep learning; evolutionary computation; neuroevolution
Show Figures

Figure 1

MDPI and ACS Style

Divina, F.; Torres Maldonado, J.F.; García-Torres, M.; Martínez-Álvarez, F.; Troncoso, A. Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting. Appl. Sci. 2020, 10, 5487. https://doi.org/10.3390/app10165487

AMA Style

Divina F, Torres Maldonado JF, García-Torres M, Martínez-Álvarez F, Troncoso A. Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting. Applied Sciences. 2020; 10(16):5487. https://doi.org/10.3390/app10165487

Chicago/Turabian Style

Divina, Federico, José F. Torres Maldonado, Miguel García-Torres, Francisco Martínez-Álvarez, and Alicia Troncoso. 2020. "Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting" Applied Sciences 10, no. 16: 5487. https://doi.org/10.3390/app10165487

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop