The innovative optimization techniques for forecasting the energy consumption of buildings using the shuffled frog leaping algorithm and different neural networks

Yiran Yang, Gang Li, Tao Luo, Mohammed Al-Bahrani, Essam A. Al-Ammar, Mika Sillanpaa, Shafaqat Ali and Xiujuan Leng

Energy, 2023, vol. 268, issue C

Abstract: The heating and Cooling loads are the main contributors to energy consumption in buildings, and predicting them can prevent many potential financial losses in civil engineering projects. Using the benefits of the neural networks, including support vector machine, gated recurrent unit, extreme learning machine, long short-term memory, and shuffled frog leaping algorithm as an optimizer, the present study aims to predict the energy consumption of the building. The empirical data are trained using the selected networks and optimized through a shuffled frog-leaping algorithm. Also, the statistical criteria are analyzed to specify the best network in terms of accuracy and speed. The obtained results and the convergence rate represent the remarkable capability of the shuffled frog leaping algorithm for optimization. According to the statistical results, long short-term memory and support vector machine are introduced as the best neural network for cooling and heating load forecast, respectively. According to the obtained results, for the cooling load prediction, LSTM-SFLA presents the best performance by an R2 of 0.9761. On the other hand, for the heating load prediction, SVR-SFLA has the optimal performance with an R2 of 0.9583. The results indicate that using the SFLA optimizer could assist in improving the prediction performance.

Keywords: Building energy forecast; Machine learning models; Optimization techniques; Statistical indicators (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222034351
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:268:y:2023:i:c:s0360544222034351

DOI: 10.1016/j.energy.2022.126548

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().