This paper discusses the use of a building thermal analysis methodology in which the stochastic nature of the external climates and randomness of physical parameters are considered. Methods of thermal calculation which give the density function of the room air temperature and heating and/or cooling loads are proposed. Weather data is modeled by linear time series models with white noises as inputs, which take into account the auto-correlations and cross-correlations of the raw climatic data.
For the heating of buildings occupied on a discontinuous basis, intermittent heating control devices are used. This article presents one which incorporates advanced automatic control techniques (predictive temperature control and adaptation of the internal model). The results obtained are compared with those achieved using standard control devices. They are validated on the installation used to determine the initial settings and on slightly different installations in order to compare their robustness with respect to the various characteristics of the heating loop and of the building.