Abstract
Time series forecasting is crucial in various domains, including finance, meteorology, economics, and energy management. Regression trees and deep learning models are among the techniques developed to tackle these challenges. This paper presents a comparative analysis of these approaches in terms of efficacy and efficiency, using real-world datasets. Our experimental results indicate that regression trees can provide comparable performance to deep neural networks with significantly lower computational demands for training and hyper-parameter selection. This finding underscores the potential of regression trees as a more sustainable and energy-efficient approach to time series forecasting, aligning with the ongoing efforts in Green AI research. Specifically, our study reveals that regression trees are a promising alternative for short-term forecasting in scenarios where computational efficiency and energy consumption are critical considerations, without the need for costly GPU computation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Quinlan, J.R., et al.: Learning with continuous classes. In: 5th Australian Joint Conference on Artificial Intelligence, vol. 92, pp. 343–348. World Scientific (1992)
Gardner, M.W., Dorling, S.R.: Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences. Atmosp. Environ. 32(14-15), 2627–2636 (1998)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Lim, B., Arık, S.Ö., Loeff, N., Pfister, T.: Temporal fusion transformers for interpretable multi-horizon time series forecasting. Int. J. Forecast. 37(4), 1748–1764 (2021)
Silva, P., et al.: Approximation workflow for energy-efficient comparators in decision tree applications. In: 2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC), pp. 1–2. IEEE (2022)
Mohammed, A., et al.: ANN, M5P-tree and nonlinear regression approaches with statistical evaluations to predict the compressive strength of cement-based mortar modified with fly ash. J. Market. Res. 9(6), 12416–12427 (2020)
Kuo, J.C.-C., Madni, A.M.: Green learning: introduction, examples and outlook. J. Vis. Commun. Image Represent. 90, 103685 (2022)
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)
Gocheva-Ilieva, S.G., et al.: Regression trees modeling of time series for air pollution analysis and forecasting. Neural Comput. Appl. 31, 9023–9039 (2019)
Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual Conference, vol. 35, pp. 11106–11115. AAAI Press (2021)
Jiménez-Navarro, M.J., Martínez-Ballesteros, M., Martínez-Álvarez, F., Asencio-Cortés, G.: A new deep learning architecture with inductive bias balance for transformer oil temperature forecasting. J. Big Data 10(1), 80 (2023)
REE: Red El’ectrica de España (2015)
Lara-Benítez, P., Carranza-García, M., Riquelme, J.C.: An experimental review on deep learning architectures for time series forecasting. Int. J. Neural Syst. 31(03), 2130001 (2021)
Torres, J.F., Hadjout, D., Sebaa, A., Martínez-Álvarez, F., Troncoso, A.: Deep learning for time series forecasting: a survey. Big Data 9(1), 3–21 (2021)
Acknowledgments
This research has been funded by Ministerio de Ciencia e Innovación under the projects: Aprendizaje Profundo y Transferencia de Aprendizaje Eficientes para Salud y Movilidad (PID2020-117954RB-C22), and Soluciones Digitales para Mantenimiento Predictivo de Plantas Eólicas (TED2021-131311B); and by the Andalusian Regional Government under the project Modelos de Deep Learning para Sistemas de Energía Renovable: Predicción de Generación y Mantenimiento Preventivo y Predictivo (PYC20 RE 078 USE).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Reina-Jiménez, P., Carranza-García, M., María Luna-Romera, J., C. Riquelme, J. (2023). Efficient Short-Term Time Series Forecasting with Regression Trees. In: García Bringas, P., et al. 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023). SOCO 2023. Lecture Notes in Networks and Systems, vol 750. Springer, Cham. https://doi.org/10.1007/978-3-031-42536-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-42536-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42535-6
Online ISBN: 978-3-031-42536-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)