Load Forecasting with Machine Learning and Deep Learning Methods
Applied Sciences · 06.07.2023 · 13 (13) · 7933
DOI: 10.3390/app13137933 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.07.2023. Verfasst von Moisés Cordeiro-Costas und 4 weiteren Autor:innen. Die Arbeit wurde bisher 118-mal zitiert (Crossref) und nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Innovation and Universities of the Spanish Government, Universidade de Vigo, European Group for territorial cooperation Galicia-North of Portugal (GNP, AECT) through the IACOBUS program of research stays.
Abstract (Originalsprache)
Characterizing the electric energy curve can improve the energy efficiency of existing buildings without any structural change and is the basis for controlling and optimizing building performance. Artificial Intelligence (AI) techniques show much potential due to their accuracy and malleability in the field of pattern recognition, and using these models it is possible to adjust the building services in real time. Thus, the objective of this paper is to determine the AI technique that best forecasts electrical loads. The suggested techniques are random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), long short-term memory (LSTM), and temporal convolutional network (Conv-1D). The conducted research applies a methodology that considers the bias and variance of the models, enhancing the robustness of the most suitable AI techniques for modeling and forecasting the electricity consumption in buildings. These techniques are evaluated in a single-family dwelling located in the United States. The performance comparison is obtained by analyzing their bias and variance by using a 10-fold cross-validation technique. By means of the evaluation of the models in different sets, i.e., validation and test sets, their capacity to reproduce the results and the ability to properly forecast on future occasions is also evaluated. The results show that the model with less dispersion, both in the validation set and test set, is LSTM. It presents errors of −0.02% of nMBE and 2.76% of nRMSE in the validation set and −0.54% of nMBE and 4.74% of nRMSE in the test set.
Förderung
- Ministry of Science, Innovation and Universities of the Spanish Government
- Universidade de Vigo
- European Group for territorial cooperation Galicia-North of Portugal (GNP, AECT) through the IACOBUS program of research stays
Zitieren
APA
Cordeiro-Costas, M., Villanueva, D., Eguía-Oller, P., Martínez-Comesaña, M., & Ramos, S. (2023). Load Forecasting with Machine Learning and Deep Learning Methods. Applied Sciences, 13(13), 7933. https://doi.org/10.3390/app13137933
Vancouver
Cordeiro-Costas M, Villanueva D, Eguía-Oller P, Martínez-Comesaña M, Ramos S. Load Forecasting with Machine Learning and Deep Learning Methods. Applied Sciences. 2023;13(13):7933. doi:10.3390/app13137933
BibTeX
@article{CordeiroCostas2023,
author = {Cordeiro-Costas, Moisés and Villanueva, Daniel and Eguía-Oller, Pablo and Martínez-Comesaña, Miguel and Ramos, Sérgio},
title = {Load Forecasting with Machine Learning and Deep Learning Methods},
journal = {Applied Sciences},
year = {2023},
volume = {13},
number = {13},
pages = {7933},
doi = {10.3390/app13137933}
}
EUVIMED