Ventilation systems are deployed in buildings to maintain good indoor air quality, especially in specific periods, or in the absence of buildings’ windows. These systems perform automatically this task by regulating the injected air according to the actual indoor CO2 concentration. Several control approaches have been implemented and deployed in real-setting scenarios, but most of them are either time-triggered or based on fixed threshold values. In this paper, we introduce a platform that integrates recent advanced Internet of Things and big-data technologies for context-driven monitoring and control of ventilation systems. The aim is to gather, process and extract contextual data, mainly indoor/outdoor CO2 concentration, to be used for maintaining a suitable ventilation rate that balances between energy consumption and occupants’ well-being. A prototype was developed and deployed for conducting experiments of different ventilation control approaches. We have developed two control approaches, ON/OFF and proportional–integral–derivative control, and compared them with the proposed state-feedback control approach. Experiments have been conducted in our Energy-Efficient Building Laboratory to evaluate these approaches in terms of the indoor CO2 concentration, the ventilation rates, and the power consumption. The experimental results show that the state-feedback control outperforms proportional–integral–derivative and ON/OFF control approaches in terms of energy efficiency and comfort.
Big Data acquired by Internet of Things-enabled industrial multichannel wireless sensors networks for active monitoring and control in the smart grid Industry 4.0
