Online and Compositional Learning of Controllers with Application to Floor Heating

Controller synthesis for stochastic hybrid switched systems, like e.g. a floor heating system in a house, is a complex computational task that cannot be solved by an exhaustive search though all the control options. The state-space to be explored is in general uncountable due to the presence of continuous variables (e.g. temperature readings in the different rooms) and even after digitization, the state-space remains huge and cannot be fully explored. We suggest a general and scalable methodology for controller synthesis for such systems. Instead of off-line synthesis of a controller for all possible input temperatures and an arbitrary time horizon, we propose an on-line synthesis methodology, where we periodically compute the controller only for the near future based on the current sensor readings. This computation is itself done by employing machine learning in order to avoid enumeration of the whole state-space. For additional scalability we propose and apply a compositional synthesis approach. Finally, we demonstrate the applicability of the methodology to a concrete floor heating system of a real family house.