The application of automation technology to residential environments holds a lot of benefits. Still, much of the potential available in a typical present-day home automation system lies fallow since the control strategies linking sensors and actuators are not as flexible as they should be. Tuning such a system precisely to the requirements of its users and the characteristics of both building structure and building services equipment is a task reserved to those with specialist knowledge. Moreover, it is almost never done in full due to the large effort required. For the same reason, once the system is installed, necessary readjustments are foregone almost as a rule. The task gets even harder as more design disciplines are involved. Therefore, intelligent homes that utilize modern computer technology to autonomously govern and constantly adapt the building environment to optimize both user comfort and energy-consumption simultaneously are in dire need.  ThinkHome is an incarnation of such an intelligent home of the future that utilizes artificial intelligence (AI) to improve control of home automation functions provided by dedicated automation systems. It is able to detect and utilize patterns to provide a better, more energy-efficient, yet comfort oriented, control of building functions. Primary targets are functions that require comparably high amounts of energy, such as those found in heating/ventilation and air-conditioning, and lighting/shading. For an optimization, the system must be capable of detecting user interactions and desires, to identify patterns in these data and to be able to learn and adapt to its environment. ThinkHome must therefore be able to perceive its environment, especially the home in which it is employed. It has to learn environmental parameters such as thermal inertia and combine this knowledge together with various parameters and data found in and around today’s buildings (presence, occupancy, temperature, daylight …) to find an optimal strategy for controlling the environment. Ultimate goal of the ambitious project is to prove that ThinkHome can fulfill all the demands mentioned above. This includes the definition of a knowledge base that holds all relevant data. This knowledge base is fundamental to enable our vision of optimized, AI based control strategies that allow maximizing energy efficiency. To maximize the usefulness of AI, different approaches have to be investigated and evaluated regarding their performance and output when both energy efficiency and user comfort are taken into account.

An agent based framework is home for agents that act on behalf of users (avatars) and has the artificial control strategies embedded. Moreover, it provides access to the knowledge base and interfaces to the underlying building control systems. The project outcome will be verified by a prototype implementation that will be installed into an existing building automation model. Additionally, a simulation shall highlight both the applicability and benefits that ThinkHome holds in real world projects.

From its beginning, all results of the ThinkHome project will be made available to the public through open workshops and via a dedicated project homepage.