Comparative study between two architectures of neural networks used for identification and control of a building heating system

Abstract : Nowadays the decrease of energy consumption is a world target and it is no longer feasible to design a system without concerning to the energy optimization. An important energy consumer is associated with building heating systems. The main objective of this paper is to make a comparative study between two neural network architectures; the first is not recurrent, Radial Basis Function (RBF) and the second recurrent, Recurrent Memory Neural Networks (RMNN) for the adaptive control strategy to control the heating system from one room in order to minimize energy without reducing the comfort of occupants. The method was applied to an electric heating system, and the validity and performance of the proposed control system have been shown by various simulations, using the SIMBAD toolbox.
Document type :
Conference papers
Complete list of metadatas

https://hal-centralesupelec.archives-ouvertes.fr/hal-01442664
Contributor : Hervé Guéguen <>
Submitted on : Friday, January 20, 2017 - 6:20:02 PM
Last modification on : Wednesday, January 30, 2019 - 3:22:09 PM

Identifiers

Citation

Ahmed Ouaret, Hocine Lehouche, Boubekeur Mendil, Siham Fredj, Hervé Guéguen. Comparative study between two architectures of neural networks used for identification and control of a building heating system. 2016 8th International Conference on Modelling, Identification and Control (ICMIC), Nov 2016, Algier, Algeria. ⟨10.1109/ICMIC.2016.7804232⟩. ⟨hal-01442664⟩

Share

Metrics

Record views

329