MOGA design of neural network predictors of inside temperature in public buildings

Ruano, Antonio; Crispim, E. M.; Frazão, P. M.

http://hdl.handle.net/10400.1/2234

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Ruano_Chapter_SCBMIS.pdf		794.25 KB	Adobe PDF	Download

Send Feedback

Authors

Ruano, Antonio

Crispim, E. M.

Frazão, P. M.

Abstract(s)

The use of artificial neural networks in various applications related with energy management in buildings has been increasing significantly over the recent years. In this chapter, the design of inside air temperature predictive neural network models, to be used for predictive thermal comfort control, is discussed. The design is based on the joint use of multi-objective genetic (MOGA) algorithms, for selecting the network structure and the network inputs, and a derivative algorithm, for parameter estimation. Climate and environmental data from a secondary school located in the south of Portugal, collected by a remote data acquisition system, are used to generate the models. By using a sliding window adaptive methodology, the good results obtained off-line are extended throughout the whole year.

URI

http://hdl.handle.net/10400.1/2234

Citation

Ruano, A. E.; Crispim, E. M.; Frazão, P. M. MOGA Design of Neural Network Predictors of Inside Temperature in Public Buildings, In Soft Computing Based Modeling in Intelligent Systems, 35-61, ISBN: 978-3-642-00447-6. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009.