Generation of Data for Artificial Intelligence Applications in the Building Sector

In the bigger part of buildings in Germany the temperature of a room is controlled via standard controllers like P-, PI- or PID controllers or hysteresis controllers. They are widely used because of there simple operation principles and there easy installation. Unfortunately it is often unknown what the optimal controller for the room would be. This depends among others on the geometry of the room, its wall mounting, the size and orientation of its windows, its technical equipment, its heating facility, its position including weather and its usage. To quantify this relation between a room and its optimal controller one possibility is to use Artificial Neural Networks (ANN). The drawback of those ANN is, that they need a great number of data. This submission to Winter Simulation Conference 2020 shows a possible way to generate such a big number of data to determine the relation of a room and its optimal controller by using modelling and variant simulation. Based on four room models that are modelled with the BuildingSystems library in Modelica, the tool GridWorker is used to vary room parameters and at the same time to optimize the controller parameters according to the varied room models.