Input Convex Neural Networks for Building MPC
OPEN ACCESS
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
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 multi- step 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.
Permanent link
Publication status
published
Book title
Proceedings of the 3rd Conference on Learning for Dynamics and Control
Journal / series
Volume
144
Pages / Article No.
251 - 262
Publisher
PMLR
Event
3rd Conference on Learning for Dynamics and Control (L4DC 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
03751 - Lygeros, John / Lygeros, John
09563 - Zeilinger, Melanie / Zeilinger, Melanie