HABISOL - HABISOL : Habitat Intelligent et Solaire 

AIde à la DEcision, Détection et Diagnostic de Defauts pour l'énergie dans le bâtiment – AIDE-3D

The aim of this project is to establish the scientific basis for a management and energy consumption monitoring toolin buildings, multi-fluids and multisite. These tools, operating on the basis of automatic energy consumption measurements and standardized buildings information, will provide fast, simple and effective descision-making support in terms of actions to reduce energy consumption.
The expert module developed provide, from the energy monitoring performed, and from standardized information on building, an automatic fault detection system. If an abnormality is found, a questionnaire can offer the causes of dysfunction and curative action to undertake.
In parallel, a diagnostic tool used to assess the efficiency of various building components. Building retrofit actions are proposed, and their relevance is evaluated. If some actions are implemented, energy savings measurement is conducted.

This project has enabled the development and implementation of a family of probability distributions reduced to the logistic regression ( multinomial or not). It is then possible to make a categorical classification of solutions from continuous variables. In the case of modeling the thermal behavior of a building , it means to connect the DPE based on its technical specifications and / or the data of energy consumption.
Difficulties have been encountered in the development of models. Our first attempts to complex Bayesian networks (ie with a large number of variables) have not yielded conclusive results as probability distributions were too broad. The «gray box« approach was more successful because it greatly reduced the number of variables. Very clear correlations are then emerged between some variables ( eg, age and energy efficiency) .

The approach proposed statistical analysis has shown his interest and must be valued in some very specific cases . Nonetheless an important adaptation of the analysis model for each type of building is essential , and requires some expertise.
Thus, the deployment as part of a «generalist« commercial use of such a tool seems out of reach in the current state of knowledge. Indeed, the cost of adapting the model to each case are too high in relation to the initial objectives , namely to be able to offer expertise at low cost .
It must still be noted that the work done, gain real knowledge in the mastery of the indicators and influential to follow through energy monitoring parameters of a building

Thanks to this work, a specific «energy management« offer was developed large multi-site customers. This is particularly true in the field of Banking & Insurance networks. Today we follow more than 500 buildings in France. It should be noted however that this not a full Bayesian analysis is carried out in this context, such as might be initially imagined at the beginning of the project.
As far as Probayes is concerned, the main technical benefits of this project are the knowledge and skills acquired in the field of buildings thermal modeling. In the context of the “Grenelle de l’Environment”, local authorities “Agenda 21” and “energy transition” ahead, it allows us to position Probayes on buoyant market in order to continue to develop innovative and effective applications.

CETHIL Publications in inetrnational A rank Journal
• I. Hazyuk, C. Ghiaus, D. Penhouet (2012). Optimal temperature control of intermittently heated buildings using Model Predictive Control: Part I – Building modeling. Building and Environment. 51: 379-387
dx.doi.org.scopeesprx.elsevier.com/10.1016/j.buildenv.2011.11.009

• I. Hazyuk, C. Ghiaus, D. Penhouet (2012). Optimal temperature control of intermittently heated buildings using Model Predictive Control: Part II – Control algorithm. Building and Environment. 51: 388-394
dx.doi.org.scopeesprx.elsevier.com/10.1016/j.buildenv.2011.11.008

• I. Naveros, P. Bacher, D.P. Ruiz, M.J. Jiménez, H. Madsen (2014) Setting up and validating a complex model for a simple homogeneous wall, Energy and Buildings, 70 : 303-317, dx.doi.org/10.1016/j.enbuild.2013.11.076.

Project coordination

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

Help of the ANR 0 euros
Beginning and duration of the scientific project: - 0 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter