No abstract

In this paper we present predictive selfprogramming thermostat which controls the heating of a smart environment based on occupancy prediction. We present results of 290 days-long simulation as well as limits of similar systems for energy savings.

Significant developments of technology over the last years, especially in pervasive/ubiquitous computing, have made the dream of smart environment technology true. Merging of this technology with mathematical prediction apparatus allowed raising a new level of smart environments -automating the routine control tasks and pro-active interaction. This paper deals with the potential of automation of the routine control tasks to significantly improve human experience in our houses, offices, buildings and environments in general. We present advantages, shortcomings and upcoming challenges of this technology, stateof-the-art research results as well as the results of our original research in focused area.