Multi-objective optimization of shading devices using ensemble machine learning and orthogonal design of experiments

Buildings are significant sources of energy consumption due to the non-optimal configuration of shading devices that results in excessive solar heat gain. Amorphous optimization of shading devices has not been explored in-depth using sophisticated modelling tools despite research efforts to optimize shading devices for different objectives such as energy consumption and occupant comfort. This study introduces updates to the existing framework for optimizing shading devices for multiple objectives. The objectives include occupants' thermal Discomfort Hours (DH), Heating and Cooling loads (H/C), and total shading devices' surface area. The existing framework in literature follows three main phases including data gen-eration, Machine Learning (ML) models development, and optimization. In this study, three updates to the mentioned framework are proposed: First, the optimization of fixed shading devices is performed amorphously for maximizing the occupants' thermal comfort; Second, the use of orthogonally structured training dataset to develop ML models; Third, incorporating the modern technique of Multi-Objective Manta-Ray Foraging Optimizer (MOMRFO) in the optimization phase. For only perimeter zones, amor-phous shading devices can incur a maximum 12.7 % of H/C compared to the present situation of the case study when optimized for the H/C objective, while a maximum 2.8 % of DH can be saved compared to the present situation of the case study when optimized for the DH objective. Also, it is found that the payback period becomes high (18.35 years) when the DH objective is prioritized over other objectives. The study introduces a framework that couples orthogonal design of experiment with ensemble ML models to opti-mize the geometrical configuration of amorphous shading devices.(c) 2023 Elsevier B.V. All rights reserved.

Automated summary

Buildings contribute significantly to energy consumption due to suboptimal shading device configurations that result in excessive solar heat gain. While previous research has aimed at optimizing shading devices for different objectives, such as energy consumption and occupant comfort, there is a lack of in-depth exploration on the amorphous optimization of shading devices using sophisticated modeling tools. This study presents updates to an existing framework for optimizing shading devices for multiple objectives, including occupants' thermal discomfort, heating and cooling loads, and total shading devices' surface area. The updates include amorphous optimization of fixed shading devices, the use of orthogonally structured training datasets for machine learning model development, and the incorporation of the modern Multi-Objective Manta-Ray Foraging Optimizer (MOMRFO) technique in the optimization phase.