Adaptive neural network based control approach for building energy control under changing environmental conditions

Lilli Frison, Simon Gölzhäuser
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:1741-1752, 2024.

Abstract

Deep neural networks are adept at modeling complex relationships between input and output variables. When trained on diverse datasets, they can understand not just the specifics of individual objects but also the broader principles governing an entire object class. This research applies this principle to building heating control, a domain marked by significant heterogeneity and constant environmental changes, including renovations and changes in user behavior. Our approach involves training the network on a wide range of data instances, enhancing its adaptability to newly distributed data representing unseen scenarios. We find that Transformer-based LSTM architectures are particularly adept for this task as they are able to remember previous tasks’ learning. We propose a simple yet effective control algorithm that separates system identification and forecasting from the optimization-based control step. This separation simplifies the control process while ensuring robust performance. In a wide range of simulation experiments, we demonstrate that our “universally trained” neural network control can adjust to changing conditions, thus reducing the need for more complex continual learning techniques. Our results suggest that training neural networks on varied datasets empowers the network with the ability to generalize and adapt beyond specific training instances, which demonstrates their effectiveness in dynamic and heterogeneous environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-frison24a, title = {Adaptive neural network based control approach for building energy control under changing environmental conditions}, author = {Frison, Lilli and G\"{o}lzh\"{a}user, Simon}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {1741--1752}, year = {2024}, editor = {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis}, volume = {242}, series = {Proceedings of Machine Learning Research}, month = {15--17 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v242/frison24a/frison24a.pdf}, url = {https://proceedings.mlr.press/v242/frison24a.html}, abstract = {Deep neural networks are adept at modeling complex relationships between input and output variables. When trained on diverse datasets, they can understand not just the specifics of individual objects but also the broader principles governing an entire object class. This research applies this principle to building heating control, a domain marked by significant heterogeneity and constant environmental changes, including renovations and changes in user behavior. Our approach involves training the network on a wide range of data instances, enhancing its adaptability to newly distributed data representing unseen scenarios. We find that Transformer-based LSTM architectures are particularly adept for this task as they are able to remember previous tasks’ learning. We propose a simple yet effective control algorithm that separates system identification and forecasting from the optimization-based control step. This separation simplifies the control process while ensuring robust performance. In a wide range of simulation experiments, we demonstrate that our “universally trained” neural network control can adjust to changing conditions, thus reducing the need for more complex continual learning techniques. Our results suggest that training neural networks on varied datasets empowers the network with the ability to generalize and adapt beyond specific training instances, which demonstrates their effectiveness in dynamic and heterogeneous environments.} }
Endnote
%0 Conference Paper %T Adaptive neural network based control approach for building energy control under changing environmental conditions %A Lilli Frison %A Simon Gölzhäuser %B Proceedings of the 6th Annual Learning for Dynamics & Control Conference %C Proceedings of Machine Learning Research %D 2024 %E Alessandro Abate %E Mark Cannon %E Kostas Margellos %E Antonis Papachristodoulou %F pmlr-v242-frison24a %I PMLR %P 1741--1752 %U https://proceedings.mlr.press/v242/frison24a.html %V 242 %X Deep neural networks are adept at modeling complex relationships between input and output variables. When trained on diverse datasets, they can understand not just the specifics of individual objects but also the broader principles governing an entire object class. This research applies this principle to building heating control, a domain marked by significant heterogeneity and constant environmental changes, including renovations and changes in user behavior. Our approach involves training the network on a wide range of data instances, enhancing its adaptability to newly distributed data representing unseen scenarios. We find that Transformer-based LSTM architectures are particularly adept for this task as they are able to remember previous tasks’ learning. We propose a simple yet effective control algorithm that separates system identification and forecasting from the optimization-based control step. This separation simplifies the control process while ensuring robust performance. In a wide range of simulation experiments, we demonstrate that our “universally trained” neural network control can adjust to changing conditions, thus reducing the need for more complex continual learning techniques. Our results suggest that training neural networks on varied datasets empowers the network with the ability to generalize and adapt beyond specific training instances, which demonstrates their effectiveness in dynamic and heterogeneous environments.
APA
Frison, L. & Gölzhäuser, S.. (2024). Adaptive neural network based control approach for building energy control under changing environmental conditions. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:1741-1752 Available from https://proceedings.mlr.press/v242/frison24a.html.

Related Material