This study aimed to develop a control algorithm that can operate a variable refrigerant flow (VRF) cooling system with optimal set-points for the system variables. An artificial neural network (ANN) model, which was designed to predict the cooling energy consumption for upcoming next control cycle, was embedded into the control algorithm. By comparing the predicted energy for the different set-point combinations of the control variables, the control algorithm can determine the most energy-effective set-points to optimally operate the cooling system. Two major processes were conducted in the development process. The first process was to develop the predictive control algorithm which embedded the ANN model. The second process involved performance tests of the control algorithm in terms of prediction accuracy and energy efficiency in computer simulation programs. The results revealed that the prediction accuracy between simulated and predicted outcomes proved to have a low coefficient of variation root mean square error (CVRMSE) value (10.30%). In addition, the predictive control algorithm markedly saved the cooling energy consumption by as much as 28.44%, compared to a conventional control strategy. These findings suggest that the ANN model and the control algorithm showed potential for the prediction accuracy and energy-effectiveness of VRF cooling systems.

There is an increasing number of randomized clinical trials intended to assess the effectiveness of indoor air cleaners for improving participant outcomes in real-world settings. In this communication, we synthesize the current state of registered air cleaner intervention trials and call attention to the critical importance of conducting measurements to characterize the performance and in situ utilization of air cleaners in such trials to improve interpretation of exposure measurements and patient outcomes. We draw upon the existing literature and preliminary findings from our ongoing one-year, randomized, single-blind, placebo-controlled case-control trial of stand-alone air filtration in the homes of U.S. military Veterans to inform our recommendations. We demonstrate how to conduct industry-standard performance testing and how to use long-term measurements of air cleaner power draw to assess air cleaner operation. In our analysis of interim data from 53 homes to date with a mean data collection period of 275 days, we found that most air cleaners, whether active or sham, were operated predominantly at low or medium fan speeds, and most participants operated their air cleaner on predominantly one fan speed. In a few homes, air cleaners were mostly off. We estimate that air cleaner operation in these homes is providing a median additional equivalent particle loss rate of ∼0.7/h (ranging ∼0–2.8/h). Accordingly, we recommend that air cleaner intervention trials adopt the steps described herein to account for the amount of clean air delivered in real-world settings and to provide important context alongside indoor exposure measurements and analysis of patient outcomes.

Background: Evidence linking exposure to airborne particulate and gaseous pollutants, as well as mold spores, with asthma control and severity is well established. A growing body of literature has demonstrated that ventilation and air filtration can improve indoor air quality (IAQ); however, clinical evidence on their comparative health impacts remains limited. Therefore, this trial aims to evaluate the long-term effectiveness of energy recovery ventilators (ERVs) and portable air cleaners (PACs) in reducing indoor air pollutants and mold levels and improving health outcomes in individuals with asthma. Secondary objectives includes associations between housing conditions, occupant behaviors, indoor environmental exposures, and asthma-related health outcomes. Methods: The AIRVAC study is a single-blind, placebo-controlled, 4-arm, parallel-group, randomized controlled trial, with a pre-intervention period of up to 1 year and a 1-year post-intervention period. Children aged 5–17 years and adults with physician-diagnosed asthma will be recruited from more than 80 households across the Dallas-Fort Worth (DFW) area in Texas. Following the pre-intervention period, each household will be randomized to receive one of four different interventions midway through the study: (1) active ERVs, (2) sham ERVs, (3) active PACs, and (4) sham PACs. Primary health outcomes include asthma control; secondary outcomes include pulmonary function, asthma-related quality of life, stress, and sleep quality. Initial housing assessments will be conducted prior to the pre-intervention period to characterize occupant behaviors and housing-related factors that may contribute to asthma exacerbations and affect ERV installation. Environmental exposures will be assessed by combining measurements of indoor and outdoor air pollutants, including particulate matter (PM), nitrogen dioxide (NO ₂ ), carbon monoxide (CO), and volatile organic compounds (VOCs), as well as temperature, relative humidity, and indoor and outdoor mold, using low-cost and research-grade air quality sensors and mold sampling methods. Discussion: Findings from the AIRVAC study will provide important evidence on the comparative effects of residential ventilation and air cleaning interventions on IAQ, mold, and asthma-related health outcomes among children and adults with asthma. The study will also examine the relationships among housing characteristics, occupant behaviors, indoor environmental exposures, and asthma-related health outcomes, while providing insights into the operation and performance of residential ventilation and air cleaning interventions in vulnerable households.