Artificial Neural Network-Based Modelling for Daylight Evaluations

Abstract

The climate based Daylight Autonomy (DA) metric has been gaining ground in the field of sustainable building design as a measure for the amount of daylight within spaces and associated energy savings. In this study, Artificial Neural Networks (ANNs) were used to predict DA levels in interior spaces as an alternative to computationally expensive simulations. Research was carried out in three phases of increasing complexity: First, a neural network was trained and validated for a single design space. Subsequently, the window design was altered and a neural network was trained and tested on its ability to predict DA levels according to changes in window design. Lastly, the neural network was trained to account for the effects of shading from an external obstruction. After sufficient training, the ANN, during the recall stage, was able to predict DA, on average, within 3 DA short of the simulated DA results for both the shaded and unobstructed scenario. The results obtained show the potential of neural networks as a prediction tool for estimating Daylight Autonomy.

A Novel Framework for Optimizing Indoor Illuminance and Discovering Association of Involved Variables

“…The stored output data of the DIVA plug-in were transferred and stored in the Postgres-SQL database. Then, R software was utilized to apply the brute force search algorithm based on the proposed objective function to find the optimum louver angles [29][30][31]. After calculating indoor illuminance, UDI is calculated as a metric, which represents both indoor illuminance level and discomfort glare in one scheme, as widely utilized in the field.…”

“…The annual average of UDI may be used to evaluate the annual performance of a facade. The UDI metric, which depends on both active and passive variables, is considered as a dependent variable for establishing an objective function [28][29][30][31]. The UDI is calculated not only as lower and upper thresholds but also as a useful value depending on the range of illuminance.…”