NeurOpt: Neural network based optimization for building energy management and climate control

Achin Jain, Francesco Smarra, Enrico Reticcioli, Alessandro D’Innocenzo, Manfred Morari
Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR 120:445-454, 2020.

Abstract

Model predictive control (MPC) can provide significant energy cost savings in building operations in the form of energy-efficient control with better occupant comfort, lower peak demand charges, and risk-free participation in demand response. However, the engineering effort required to obtain physics-based models of buildings for MPC is considered to be the biggest bottleneck in making MPC scalable to real buildings. In this paper, we propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. Our approach does not require building domain expertise or retrofitting of the existing heating and cooling systems. We validate our learning and control algorithms on a two-story building with 10 independently controlled zones, located in Italy. We learn dynamical models of energy consumption and zone temperatures with high accuracy and demonstrate energy savings and better occupant comfort compared to the default system controller.

Cite this Paper


BibTeX
@InProceedings{pmlr-v120-jain20a, title = {NeurOpt: Neural network based optimization for building energy management and climate control}, author = {Jain, Achin and Smarra, Francesco and Reticcioli, Enrico and D'Innocenzo, Alessandro and Morari, Manfred}, booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control}, pages = {445--454}, year = {2020}, editor = {Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie}, volume = {120}, series = {Proceedings of Machine Learning Research}, month = {10--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v120/jain20a/jain20a.pdf}, url = {https://proceedings.mlr.press/v120/jain20a.html}, abstract = {Model predictive control (MPC) can provide significant energy cost savings in building operations in the form of energy-efficient control with better occupant comfort, lower peak demand charges, and risk-free participation in demand response. However, the engineering effort required to obtain physics-based models of buildings for MPC is considered to be the biggest bottleneck in making MPC scalable to real buildings. In this paper, we propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. Our approach does not require building domain expertise or retrofitting of the existing heating and cooling systems. We validate our learning and control algorithms on a two-story building with 10 independently controlled zones, located in Italy. We learn dynamical models of energy consumption and zone temperatures with high accuracy and demonstrate energy savings and better occupant comfort compared to the default system controller.} }
Endnote
%0 Conference Paper %T NeurOpt: Neural network based optimization for building energy management and climate control %A Achin Jain %A Francesco Smarra %A Enrico Reticcioli %A Alessandro D’Innocenzo %A Manfred Morari %B Proceedings of the 2nd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2020 %E Alexandre M. Bayen %E Ali Jadbabaie %E George Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire Tomlin %E Melanie Zeilinger %F pmlr-v120-jain20a %I PMLR %P 445--454 %U https://proceedings.mlr.press/v120/jain20a.html %V 120 %X Model predictive control (MPC) can provide significant energy cost savings in building operations in the form of energy-efficient control with better occupant comfort, lower peak demand charges, and risk-free participation in demand response. However, the engineering effort required to obtain physics-based models of buildings for MPC is considered to be the biggest bottleneck in making MPC scalable to real buildings. In this paper, we propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. Our approach does not require building domain expertise or retrofitting of the existing heating and cooling systems. We validate our learning and control algorithms on a two-story building with 10 independently controlled zones, located in Italy. We learn dynamical models of energy consumption and zone temperatures with high accuracy and demonstrate energy savings and better occupant comfort compared to the default system controller.
APA
Jain, A., Smarra, F., Reticcioli, E., D’Innocenzo, A. & Morari, M.. (2020). NeurOpt: Neural network based optimization for building energy management and climate control. Proceedings of the 2nd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 120:445-454 Available from https://proceedings.mlr.press/v120/jain20a.html.

Related Material