Input Convex Neural Networks for Building MPC
This work provides a method for applying data-driven models in building MPC, which can help building operators reduce energy consumption without the high cost of first-principle models. It is an incremental improvement for a specific domain.
This paper addresses the challenge of using data-driven models in Model Predictive Control (MPC) for buildings, where real-time optimization requires convex models. The authors adapt Input Convex Neural Networks (ICNNs) to ensure convexity for multi-step ahead predictions, which is crucial for MPC. In real-life experiments, MPC with these adapted ICNNs successfully maintained room temperatures within comfort limits while minimizing cooling energy consumption over two five-day cooling periods.
Model Predictive Control in buildings can significantly reduce their energy consumption. The cost and effort necessary for creating and maintaining first principle models for buildings make data-driven modelling an attractive alternative in this domain. In MPC the models form the basis for an optimization problem whose solution provides the control signals to be applied to the system. The fact that this optimization problem has to be solved repeatedly in real-time implies restrictions on the learning architectures that can be used. Here, we adapt Input Convex Neural Networks that are generally only convex for one-step predictions, for use in building MPC. We introduce additional constraints to their structure and weights to achieve a convex input-output relationship for multistep ahead predictions. We assess the consequences of the additional constraints for the model accuracy and test the models in a real-life MPC experiment in an apartment in Switzerland. In two five-day cooling experiments, MPC with Input Convex Neural Networks is able to keep room temperatures within comfort constraints while minimizing cooling energy consumption.