Metamodeling of the Energy Consumption of Buildings with Daylight Harvesting – Application of Artificial Neural Networks Sensitive to Orientation

Abstract

Daylight harvesting is a well-known strategy to address building energy efficiency. However, few simplified tools can evaluate its dual impact on lighting and air conditioning energy consumption. Artificial neural networks (ANNs) have been used as metamodels to predict energy consumption with high precision, few input parameters and instant response. However, this approach still lacks the potential to estimate consumption when there is daylight harvesting, at the ambient level, where the effect of orientation can be noted. This study investigates this potential, in order to evaluate the applicability of ANNs as a tool to aid the architectonic design. The ANNs were approached as metamodels trained based on EnergyPlus thermo-energetic simulations. The network configuration focused on determining its simplest feasible form. The input parameters adopted as the main variables of the building envelope were as follows: orientation, window-to-wall ratio and visible transmission. The effects of the encoding of orientation as a network input parameter, the number of examples of each variable for network training and changing the parameters used for the training were evaluated. The networks predicted the individualized consumption according to the end use with errors below 5%, indicating their potential to be applied as a simplified tool to support the design process, considering the elementary variables of the building envelope. The discussion of results focused on guidelines and challenges to achieve this purpose when contemplating the broadening of the metamodel scope.

Natural light optimization in an existing primary school: human centred design and daylight retrofitting solutions for students wellbeing

“…This provides considerable reduction of mental fatigue and hyperactivity in children, as proved by recent literature researches [7,11,15]. Our methodological approach showed how any lighting project, based on the integration of natural and artificial light, should be based on the use of digital technologies, DALI wireless, tunable white drivers, widely available today, to provide light quality and vision/perception quality [1,4,23,24]. These integrated solutions not only produce people visual comfort and global well-being but, at the same time, important energy consumption reduction, with consequent positive effects on the environment.…”

“…Literature studies show the importance of controlling natural light in relation to latitude, local climate, building orientation and distribution of its internal environments, different uses and visual tasks, highlighting the advantages of its maximum use [14,[20][21][22]. It has been demonstrated how the energy sustainability and green integration solutions for buildings, provide specific evaluation criteria and visual comfort indices and the necessary natural light quantity for specific tasks, connected to the visual field of the subject [14,23].…”

“…New indexes and approaches for indoor visual/perception comfort based on corneal illuminance [2,19,20] has been investigated. Research in lighting design with focus on green sustainable and human centric lighting, has evaluated human vision and perception mechanisms in response to different effects of natural and artificial lighting and their optimal controlled combination e.g., glare sensation, colour perception, users' preferences for different luminous conditions [16,[19][20][21][22][23].…”

“…Some authors have investigated the potential of artificial neural networks, as predictive model for buildings energy consumption evaluation [23]. In particular, they have assessed the daylight harvesting combined with different orientations at the ambient level, providing a useful tool for the architecture and lighting design [23].…”