Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings

Duc-Hoc Tran, Duc-Long Luong and Jui-Sheng Chou

Energy, 2020, vol. 191, issue C

Abstract: As the global economy expands, both residential and commercial buildings consume an increasing proportion of the total energy that is used by buildings. Energy simulation and forecasting are important in setting energy policy and making decisions in pursuit of sustainable development. This work develops a new ensemble model, called the Evolutionary Neural Machine Inference Model (ENMIM), for estimating energy consumption in residential buildings based on actual data. The ensemble model combines two single supervised learning machines - least squares support vector regression (LSSVR), and the radial basis function neural network (RBFNN) –and incorporates symbiotic organism search (SOS) to find automatically its optimal tuning parameters. A set of real data, which were obtained from residential buildings in Ho Chi Minh City, Viet Nam, as well as experimental data from the literature were used to evaluate the performance of the developed model. Comparison results reveal that the ENMIM surpasses other benchmark models with respect to predictive accuracy. This work proves that the developed ensemble model is a promising alternative for the planning of energy management. Furthermore, the fact that the ENMIM has greater predictive accuracy than other artificial intelligence techniques suggests that the developed self-tuning ensemble model can be used in various disciplines.

Keywords: Energy consumption; Residential buildings; Ensemble model; Artificial intelligence; Machine learning; Evolutionary optimization (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544219322479
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:191:y:2020:i:c:s0360544219322479

DOI: 10.1016/j.energy.2019.116552

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 ().