IAQ Monitoring System Optimizing Data-Driven Sensor Placement

Indoor Air Quality (IAQ) significantly impacts people's health and comfort in buildings. Although IAQ research spans two decades, a comprehensive assessment of factors affecting indoor air pollution remains elusive. Recent efforts focus on real-time monitoring using virtual sensing, a computational technique in engineering and data science. This paper presents a novel IAQ monitoring system emphasizing dynamic sensor placement for enhanced efficiency. The system employs random sensor positions and calculates measurement predictability, allowing identification and removal of less useful sensors, reducing data volume, and saving energy. Multiple reduction strategies are available, depending on the target number of edge devices or the desired maximum prediction error. Importantly, the system operates locally, without relying on internet connectivity. It consists of edge devices using air quality sensors, a gateway for data gathering and algorithm initiation, by training and evaluating multiple different machine learning techniques to determine point combination predictability. Deployed in two indoor settings, one with HVAC and the other naturally ventilated, the system's effectiveness is assessed, shortcomings identified, and conclusions drawn for future work.