Paper Conference

Proceedings of Building Simulation 2021: 17th Conference of IBPSA

     

Predicting solar radiation with Artificial Neural Network based on urban geometrical classification

Anas Lila 1, Wassim Jabi 2, Simon Lannon 2
1 Department of Architecture and Built Environment, faculty of environment and technology, university of west england, United Kingdom
2 Welsh School of Architecture, Cardiff University


DOI: https://doi.org/10.26868/25222708.2021.30796
Abstract: This research introduces the adaptation and development of an open-source Artificial Neural Network (ANN) with the aim of predicting solar radiation for newly generated neighbourhoods in Aswan, Egypt as an example of a hot arid zone. The outcomes are the result of training the ANN on a database of classified urban geometries and their solar radiation simulation results for local weather conditions. The classification of this database was first introduced and discussed in (Lila and Lannon 2019). This paper discusses the different stages of developing the ANN code and its final version capabilities. The ANN code was developed to differentiate the training process from the prediction code to allow for the reuse of the trained ANN in multiple tests. The ANN code was tested for different database sizes to predict individual buildings’ solar radiation and was also used to predict solar radiation for urban configurations that were not part of the training process. The results of these ANN predictions were compared to conventional solar radiation simulation results to establish the accuracy and time saved.
Keywords: urban geometry, neural network, solar analysis, parametric modelling
Pages: 902 - 909
Paper:
bs2021_30796