Predictive control of indoor environment using occupant number detected by video data and CO2 concentration

The application of big data technology in the field of indoor environment can be expected to achieve creative control. A feasible application is the data fusion of temperature, humidity, CO2 concentration, illuminance, and video to achieve novel control for air-conditioners (AC), outdoor air handling units (OAHU), and luminaires. This paper proposed a predictive control method for indoor environment using occupant number detected by combining video data and CO2 concentration. The occupant numbers detected by video data and CO2 concentration are inter-calibrated to improve the detection accuracy. The predictive control based on occupant number can achieve faster response, more stable indoor environment and energy saving as well compared with traditional control of indoor environment without using the information of occupant number change. Simulation and experimental studies were conducted to verify the feasibility and effectiveness of the predictive control based on occupant number. Results show that with regard to the experimental conditions the predictive control can save OAHU energy consumption by 85.2% and total energy consumption of AC and OAHU by 39.4%. Through experiments and simulation, it is verified that the proposed occupancy-based predictive control is a promising technique to save energy consumed by heating, ventilation and air-conditioning (HVAC) system while ensuring thermal comfort and indoor air quality.

[1]  Shengwei Wang,et al.  In-situ implementation and validation of a CO2-based adaptive demand-controlled ventilation strategy in a multi-zone office building , 2011 .

[2]  Ming Jin,et al.  SoundLoc: Accurate room-level indoor localization using acoustic signatures , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[3]  Jan-Olof Dalenbäck,et al.  CO2 sensors for occupancy estimations: Potential in building automation applications , 2014 .

[4]  Burcin Becerik-Gerber,et al.  A systematic approach to occupancy modeling in ambient sensor-rich buildings , 2014, Simul..

[5]  Qing-Shan Jia,et al.  Estimation of occupancy level in indoor environment based on heterogeneous information fusion , 2010, 49th IEEE Conference on Decision and Control (CDC).

[6]  Hélène Laurent,et al.  Towards a sensor for detecting human presence and characterizing activity , 2011 .

[7]  Paul Lukowicz,et al.  Bluetooth based collaborative crowd density estimation with mobile phones , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[8]  Saandeep Depatla,et al.  Occupancy Estimation Using Only WiFi Power Measurements , 2015, IEEE Journal on Selected Areas in Communications.

[9]  Dimitrios Tzovaras,et al.  Conditional Random Fields - based approach for real-time building occupancy estimation with multi-sensory networks , 2016 .

[10]  Zheliang Chen,et al.  A novel control logic for fan coil unit considering both room temperature and humidity control , 2015 .

[11]  Yeng Chai Soh,et al.  Using unlabeled acoustic data with locality-constrained linear coding for energy-related activity recognition in buildings , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[12]  Alberto E. Cerpa,et al.  Energy efficient building environment control strategies using real-time occupancy measurements , 2009, BuildSys '09.

[13]  Hua Li,et al.  Indoor occupancy estimation from carbon dioxide concentration , 2016, ArXiv.

[14]  Yi Jiang,et al.  A new multizone model for the simulation of building thermal performance , 1997 .

[15]  Gregor P. Henze,et al.  Building occupancy detection through sensor belief networks , 2006 .

[16]  Zhang Yu-jin.  Automatic People Counting Based on Machine Learning in Intelligent Video Surveillance , 2009 .

[17]  Shaojie Tang,et al.  Electronic frog eye: Counting crowd using WiFi , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[18]  Rui Zhang,et al.  An information technology enabled sustainability test-bed (ITEST) for occupancy detection through an environmental sensing network , 2010 .

[19]  Theis Heidmann Pedersen,et al.  Establishing an image-based ground truth for validation of sensor data-based room occupancy detection , 2016 .