1. What contributions have the authors mentioned in the paper "Data-driven model predictive control using random forests for building energy optimization and climate control" ?
To overcome this problem, the authors introduce a novel idea for predictive control based on historical building data leveraging machine learning algorithms like regression trees and random forests.. The authors call this approach Data-driven model Predictive Control ( DPC ), and they apply it to three different case studies to demonstrate its performance, scalability, and robustness.. In the first case study the authors consider a benchmark MPC controller using a bilinear building model, then they apply DPC to a data-set simulated from such bilinear model and derive a controller based only on the data.. The authors compare the total amount of energy saved with respect to the classical bang-bang controller, showing that they can perform an energy saving up to 49.
read more
2. Why is the heating system switched on during the night?
Due to cold weather, which is evident from the dry-bulb temperature, the heating system is switched on during the night to maintain the thermal comfort requirements.
read more
3. What can be used as a training data for building the trees?
Besides using proxy schedule predictors, actual building equipment schedules can also be used as training data for building the trees.
read more
4. What is the primary advantage of using data-driven methods?
The primary advantage of using data-driven methods is that it has the potential to eliminate the time and effort required to build white and grey box building models.
read more
