On the Utilization of an Ensemble of Meta-Heuristics for Simulating Energy Consumption in Buildings

On the Utilization of an Ensemble of Meta-Heuristics for Simulating Energy Consumption in Buildings

Eslam Mohammed Abdelkader, Nehal Elshaboury, Abobakr Al-Sakkaf
Copyright: © 2022 |Pages: 31
DOI: 10.4018/IJAMC.296262
Article PDF Download
Open access articles are freely available for download

Abstract

Predicting energy consumption has been a substantial topic because of its ability to lessen energy wastage and establish an acceptable overall operational efficiency. Thus, this research aims at creating a meta-heuristic-based method for autonomous simulation of heating and cooling loads of buildings. The developed method is envisioned on two tiers, whereas the first tier encompasses the use of a set of meta-heuristic algorithms to amplify the exploration and exploitation of Elman neural network through both parametric and structural learning. In this regard, 10 meta-heuristic were utilized, namely differential evolution, particle swarm optimization, invasive weed optimization, teaching-learning optimization, ant colony optimization, grey wolf optimization, grasshopper optimization, moth-flame optimization, antlion optimization, and arithmetic optimization. The second tier is designated for evaluating the meta-heuristic-based models through performance evaluation and statistical comparisons. An integrative ranking of the models is achieved using average ranking algorithm.
Article Preview
Top

1 Introduction

The generation of greenhouse gases is directly proportional to energy consumption and climate change (Baldock et al., 2012; Al-Sakkaf et al., 2020). The worldwide increase in urbanization and industrialization, particularly in the building sector, has served as a major contributing factor. In this regard, the increases in energy consumption and related carbon dioxide emissions witnessed significant bumps in the last few decades, and it is expected to experience escalating increases due to rapid expansions in commercial and residential regions, and higher cooling demands in hot weather countries (Eom et al., 2020; Conevska et al., 2020). The amount of fuel consumed by this sector is equivalent to 2 billion tons of oil equivalent (TOE), representing 31% of fuel for worldwide energy use (International Energy Agency, 2015). More specifically, in terms of electricity and heating, about 0.84 billion TOE is consumed by the building sector. Moreover, the building sector consumes 12% of fresh water and contributes to 40% of global solid waste and 40% of CO2 emissions. Approximately 20 – 25% and 30 – 40% have been reported as consumed energy for developing and developed countries, respectively (Akande et al., 2015; Al-Sakkaf, et al., 2019). In the United States and European Union, up to 40% energy consumption is attributed to the building sector (Cao et al., 2016).

Based on the aforementioned points, improved sustainability in buildings is essential to reduce environmental impacts and improve the wellbeing of individuals. This is also dependent on the efficiency of several elements in buildings. For example, consumed energy in the heating and cooling processes could be managed by heating, ventilation, and air conditioning (HVAC) systems to ensure a comfortable indoor environment in buildings. Therefore, proper design of HVAC systems, based on climate and building attributes, is critical to the energy efficiency of buildings (McQuiston & Parker, 1982; Castaldo et al., 2018; Bui et al., 2019). In this regard, energy prediction models are required for facility managers to better understand sustainability in buildings (Ürge-Vorsatz et al., 2007; Egan et al., 2018; Fanti et al., 2018; Al-Sakkaf et al., 2019). Forward and inverse models are typically applied to evaluate the energy performance of buildings (Zhao et al., 2012). For forward modeling, the building attributes are utilized despite being not easily determined, decreasing the computation accuracy, increasing the computation time, and hindering the application for occupied buildings (Yezioro et al., 2008; Park et al., 2016). Inverse modeling, on the other hand, is a machine learning model that can be applied as an alternative to identify the correlation between energy consumption and building attributes or factors (Catalina et al., 2008; Yu et al., 2010; O’Neill & O’Neill, 2016). This modeling technique is easy and has a fast computation speed (Bui et al., 2019).

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing