Self-learning model predictive control for dynamic activation of structural thermal mass in residential buildings

Changes in the electricity supply system induce the challenge of matching the highly fluctuating and unpredictable renewable energy generation with the yet inflexible electricity demand. This leads to an increasing demand for energy storage and demand-flexibility. Electrification of residential heating systems in combination with advanced controls utilizing dynamically the structural thermal mass (STM) of buildings as thermal storage could provide some of the required demand flexibility. In this work, a model predictive control (MPC) algorithm is developed and applied within a simulation framework to control dynamic heating operation as a measure of STM based residential load shifting (LS). The self-learning algorithm is functional without extensive measurement data or expert knowledge for parametrization. It optimizes heating operations required for LS according to a dynamic primary energy factor signal, while observing transient thermal comfort constraints. The implemented auto-regressive black-box model with explanatory variables predicts thermal conditions within the observed thermal zone with sufficient quality to support MPC. Based on that model, the control algorithm successfully activates STM as a measure of LS according to the given primary energy (PE) oriented utility function. For the observed system, the PE demand can be reduced by 3–7% while maintaining or even improving the thermal comfort.