Sustainability, Journal Year: 2024, Volume and Issue: 17(1), P. 58 - 58
Published: Dec. 25, 2024
This paper explores innovative approaches to reducing energy consumption in building ventilation systems through the implementation of adaptive control strategies. Using a publicly available high-resolution dataset spanning full year, study integrates real-time data on occupancy, CO2 levels, temperature, window state, and external environmental conditions. Notably, occupancy derived from computer vision-based detection using YOLOv5 algorithm provides an unprecedented level granularity. The evaluates five energy-saving strategies: Demand-Controlled Ventilation (DCV), occupancy-based control, time-based off-peak reduction, window-open temperature-based control. Among these, strategy achieved highest savings, power by 50%, while yielded significant 37.27% reduction. paper’s originality lies its holistic analysis multiple dynamic strategies, integrating diverse operational variables rarely combined prior research. findings highlight transformative potential advanced algorithms optimize HVAC performance. establishes new benchmark for energy-efficient management offering practical recommendations laying groundwork predictive models, renewable integration, occupant-centric systems.
Language: Английский