Personal thermal comfort is a crucial yet often over-simplified factor in building climate control. Traditional comfort models lack the adaptability to fit individuals’ demand. Recent advances of machine learning and ubiquitous sensor networks enable the data-driven approach of thermal comfort. In this paper, we built a platform that can simulate occupants with different thermal sensations and used it to examine the performance of support vector machine (SVM) and compared with several other popular machine learning algorithms on thermal comfort prediction. We also proposed a hybrid SVM-LDA thermal comfort classifier that can improve the efficiency of model training.
Currently, design and control of HVAC system in buildings rely heavily on simulation tools. However, the common tools available often fail to optimize occupants’ comfort directly, nor do they consider real-time variations in occupancy that affect comfort and energy performance.
To address these limits, this research designed an occupancy-based and thermal comfort-driven building automation simulation model. A single-space prototype lab room was co-simulated using EnergyPlus and MATLAB with the help of BCVTB and MLE+ as middleware. Various climate scenarios from four cities in the U.S. in different seasons were examined. Results suggest that overall, compared to a conventional temperature-driven control strategy baseline, the proposed system can minimize thermal comfort violation (in term of PMV model, |PMV|>0.5 is considered as a violation) to 7% and reduce occupants’ thermal discomfort by 62.5% on average. Meanwhile, energy consumption remains same or reduced (up to 2% reduction). Due to its simplicity, this strategy is relatively easy to implement in real-world building automation systems with appropriate sensor placement in modern buildings.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.