Share

Control via learning: air-conditioning applications.

Régulation par apprentissage : application au conditionnement d'air.

Author(s) : GERASSIMOFF G., JEBALI G., PEFFER T.

Type of article: Article, Case study

Summary

The aim of this article is to demonstrate methodology making it possible to use data provided by a sensor network via machine learning methods in order to control building services automatically in a smart manner taking into account the physical properties of the building as well actual use and occupant comfort. Firstly, the methodology and experimental approach are described. Then the initial results of the implementation of a predictive control Law within a test building at Berkeley University are presented. A significant decrease in the energy consumption required for air conditioning was measured, and extrapolation to the entire building demonstrates true potential efficiency.

Details

  • Original title: Régulation par apprentissage : application au conditionnement d'air.
  • Record ID : 30024036
  • Languages: French
  • Subject: Environment
  • Source: Revue générale du Froid & du Conditionnement d'air - n.1168
  • Publication date: 2018/03

Links


See other articles in this issue (4)
See the source

Indexing