University of Twente Student Theses

Login

Surrogate Modelling of Solar Radiation Potential for the Design of PV Module Layout on Entire Façade of Tall Buildings

Barus, Meggie Vincentia (2021) Surrogate Modelling of Solar Radiation Potential for the Design of PV Module Layout on Entire Façade of Tall Buildings.

[img] PDF
1MB
Abstract:This research investigated the performance of a surrogate modelling approach for the simulation of solar radiation potential on the vertical surfaces of tall buildings. Surrogate modelling was used to approximate the input-output behaviour of the existing simulation model. The Random Forest (RF) machine learning approach was used to investigate three different scenarios, namely (1) Random variation, (2) Grid variation, and (3) Uniform variation, and a Genetic Algorithm was used as the hyperparameter optimisation. A case study using a building in Sir George William (SGW) campus of Concordia University in downtown Montreal Canada was performed to investigate the performance of surrogate models. As a result, even by only using a small sample size of the dataset when developing the RF, surrogate modelling can give 94% accuracy to approximate the simulation of solar radiation. From the three scenarios, the best accuracy is obtained when using the Random variation method. In short, the solar radiation simulation is very complex and too sensitive to the location and shadow effect. Therefore, simplification of those factors cannot be made to approximate the solar radiation potential. Also, using RF, the computational time improved by 16 times faster than when using the existing simulation model.
Item Type:Essay (Master)
Faculty:ET: Engineering Technology
Programme:Construction Management and Engineering MSc (60337)
Link to this item:https://purl.utwente.nl/essays/88896
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page