Evaluation and Parametric Optimization of the Heating Load and Comfort Conditio...

• Author(s): Almeida, Ricardo ; Freitas, Vasco Peixoto
• Date: 2011
• Persistent ID: http://hdl.handle.net/10400.19/1925
• Origin: Repositório Científico do Instituto Politécnico de Viseu
• Subject(s): Building simulation; Energy efficiency; Thermal comfort; Artificial neural networks
• Document Type: Conference Object
• Language: English

Description

This paper presents a study on the performance of a school building and on how to improve it. For that five construction elements properties were analysed: the heat transfer coefficient of external walls, roof, and windows, the total solar energy transmittance of windows and the air change rate. The school building behaviour was evaluated by means of two performance functions, one related with the annual heating load and the other with the thermal discomfort due to overheating. Since the calculation of these functions involves the annual simulation of the buildings, and this is a very time consuming procedure, it is almost impossible to perform this type of study on a direct manner. To overlap this issue, Artificial Neural Networks were trained and then used to approximate the functions.