Predicting occupancy counts using physical and statistical Co 2 -based modeling methodologies

Abstract Energy consumption and indoor environment quality (IEQ) of buildings have been linked to human occupants. Predicting the number of occupants in a space is essential for the effective management of various building operation functions as well as improve energy efficiency. This study is the first to compare the performance of physical and statistical models in predicting occupant counts in a high volume lecture theatre (Occ = 200) using CO 2 sensors. CO 2 measurements and actual occupant numbers were obtained for 4 months to provide robust data comparison of the methodologies. It was found that that the dynamic physical models and Support Vector Machines (SVM) and Artificial Neural Networks (ANN) models utilizing a combination of average and first order differential CO 2 concentrations performed the best in terms of predicting occupancy counts with the ANN and SVM models showing higher predictive performance. RMSE values for the corresponding models were 12.8, 12.6 and 12.1 respectively and correlation coefficients were all greater than 0.95. The relatively good agreement between dynamic physical model predictions and ground truth shows that the dynamic mass balanced model is adequate for predicting occupancy counts provided that the air exchange rates measured are accurate. Model average accuracies across all tolerance was between 70 and 76% demonstrating good performance for a large number of occupants. A discussion on the merits and limitations of each model types was presented to provide guidance on the adoption of various models.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Bjarne W. Olesen,et al.  Thermal and Indoor Air Quality Effects on Physiological Responses, Perception and Performance of Tropically Acclimatized People , 2007 .

[3]  Jin Wen,et al.  Estimating building airflow using CO2 measurements from a distributed sensor network , 2011 .

[4]  Stéphane Ploix,et al.  Estimating Occupancy In Heterogeneous Sensor Environment , 2016 .

[5]  Liu Yang,et al.  Thermal comfort and building energy consumption implications - A review , 2014 .

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

[7]  P Pieter-Jan Hoes,et al.  User behavior in whole building simulation , 2009 .

[8]  Robin Nyström,et al.  Stable carbon isotope labelled carbon dioxide as tracer gas for air change rate measurement in a ventilated single zone , 2017 .

[9]  Thomas Weng,et al.  Occupancy-driven energy management for smart building automation , 2010, BuildSys '10.

[10]  Zhenghua Chen,et al.  A fusion framework for occupancy estimation in office buildings based on environmental sensor data , 2016 .

[11]  Brent Stephens,et al.  Methods to assess human occupancy and occupant activity in hospital patient rooms , 2015 .

[12]  Jiejin Cai,et al.  Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks , 2009 .

[13]  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 .

[14]  Sandhya Patidar,et al.  Understanding the energy consumption and occupancy of a multi-purpose academic building , 2015 .

[15]  Hyeun Jun Moon,et al.  Development of an occupancy prediction model using indoor environmental data based on machine learning techniques , 2016 .

[16]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[17]  Chirag Deb,et al.  Energy performance model development and occupancy number identification of institutional buildings , 2016 .

[18]  Roulet Claude-Alain,et al.  Simple and Cheap Air Change Rate Measurement Using CO2 Concentration Decays , 2002 .

[19]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[20]  Theis Heidmann Pedersen,et al.  Method for room occupancy detection based on trajectory of indoor climate sensor data , 2017 .

[21]  Kwok Wai Tham,et al.  Indoor air quality comparison of two air-conditioned zones served by the same air-handling unit , 2002 .

[22]  Shengwei Wang,et al.  CO 2-Based Occupancy Detection for On-Line Outdoor Air Flow Control , 1998 .

[23]  Shengwei Wang,et al.  Experimental Validation of CO2-Based Occupancy Detection for Demand-Controlled Ventilation , 1999 .

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

[25]  A. Persily,et al.  Carbon dioxide generation rates for building occupants , 2017, Indoor air.

[26]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[27]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[28]  J. Sundell,et al.  CO2 generation rate in Chinese people. , 2014, Indoor air.

[29]  Tianzhen Hong,et al.  Occupant behavior modeling for building performance simulation: Current state and future challenges , 2015 .

[30]  Atila Novoselac,et al.  Localized air-conditioning with occupancy control in an open office , 2010 .

[31]  Guido Bugmann,et al.  NEURAL NETWORK DESIGN FOR ENGINEERING APPLICATIONS , 2001 .

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

[33]  P. N. Smith,et al.  Determination of ventilation rates in occupied buildings from metabolic CO2 concentrations and production rates , 1988 .

[34]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[35]  M. S. Zuraimi,et al.  Tracer Gas Measurement of Airflow Rates in Spaces with Several Air-Handling Units, Recirculation, or Large Time Constants , 2005 .

[36]  Rita Streblow,et al.  CO2 based occupancy detection algorithm: Experimental analysis and validation for office and residential buildings , 2015 .

[37]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[38]  Ardeshir Mahdavi,et al.  Predicting people's presence in buildings: An empirically based model performance analysis , 2015 .