Communications of the ACM
ML Offers Shortcut to Optimal HVAC Operation
The new framework for HVAC controls that could balance efficiency, comfort, and cost without requiring significant computation time.
Credit: Maxiphoto/iStock
Pennsylvania State University (Penn State) researchers have developed a method for heating, ventilation, and air conditioning control mechanisms that uses machine learning to balance energy cost, comfort, and efficiency while enabling fast computing.
The researchers used data from model predictive controllers to train the model to determine the best times of day to cool a building.
Penn State's Gregory Pavlak said, "We used machine learning to generate a simple, easily interpretable set of rules for reducing building cooling energy and operating costs—without needing to run model predictive controllers in real time."
The best rule sets achieved 95% to 97% of the energy savings of the detailed model predictive controller, and 89% to 92% of the cost objective savings.
The method can schedule a control strategy for one day in less than a second, versus hours of computation with the original model predictive controller.
From Pennsylvania State University News
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found