IoT-Based Intelligent HVAC Energy Management for Smart Buildings: An Analysis of Sensor-Driven Control, Demand Response, Indoor Air Quality, and Electrical Energy Optimization

Abstract

The monitoring dataset from central Sweden (covering 2019-2022) is analyzed in this paper to understand how intelligent energy optimization can be implemented using sensor-driven ventilation and machine control HVAC systems. The dataset includes measurements of hourly electricity, ventilation airflow, temperature, relative humidity, CO2, and PM with time intervals of 10 mins or less. During the study period, three approaches to ventilation control were implemented: demand-controlled exhaust ventilation, flat-plate MVHR, and rotating-wheel MVHR. Since this paper performs a secondary empirical analysis on published outcomes of measured systems and does not reprocess raw sensor data, no p values have been fabricated. Out of the measures examined, demand-controlled exhaust ventilation achieved a 47 % airflow reduction factor, as compared to a 19 % guideline reference. In contrast to flat-plate constant-flow MVHR, rotating-wheel MVHR required substantially less heating power at -10 °C and 0 °C, respectively, with a higher fan power rating. During the pandemic, average daily unoccupied time reduced from 6.5 hours to 5.25 hours. Intelligent HVAC management will consider optimization of total system energy, and balanced peak and mean occupancy/IAQ response to minimize energy consumption. An IoT (Internet of Things) architecture is proposed to implement the findings.