Forecasting building occupancy: a temporal-sequential analysis and machine learning integrated approach

Abstract Building occupancy is the basis for building energy simulations, operations, and management. With the increasing need for energy conservation and the occupant-centric service of building energy systems, occupancy forecasting has become an essential input for simulations. These applications include model predictive control and demand response, with the potential to optimize the use of renewable energy sources. Based on recent research, occupancy forecasting tends to be based on occupancy data of the previous time step or continuous lagged dependent variables. Previous analysis demonstrated that building occupancy is innately temporal and sequential with seasonal features, which may be instructive for forecast research. This study proposes a temporal-sequential (TS) analysis and machine learning integrated approach for occupancy forecasting. Using hourly occupant data from 16 different buildings, we demonstrate that the proposed temporal-sequential analysis using a 1-week seasonal period with an artificial neural network structure (TS-week-ANN) outperforms other baseline methods.

[1]  Ülle Kotta,et al.  Predictive smart thermostat controller for heating, ventilation, and air-conditioning systems , 2018 .

[2]  Yacine Atif,et al.  Internet of Things data analytics for parking availability prediction and guidance , 2020, Trans. Emerg. Telecommun. Technol..

[3]  Bing Dong,et al.  Short term predictions of occupancy in commercial buildings—Performance analysis for stochastic models and machine learning approaches , 2018 .

[4]  A. Mahdavi,et al.  IEA EBC Annex 66: Definition and simulation of occupant behavior in buildings , 2017 .

[5]  Mirjana Ivanovic,et al.  BLEMAT: Data Analytics and Machine Learning for Smart Building Occupancy Detection and Prediction , 2019, Int. J. Artif. Intell. Tools.

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

[7]  Anahita Davoodi,et al.  The use of lighting simulation in the evidence-based design process: A case study approach using visual comfort analysis in offices , 2019, Building Simulation.

[8]  Bing Dong,et al.  A real-time model predictive control for building heating and cooling systems based on the occupancy behavior pattern detection and local weather forecasting , 2013, Building Simulation.

[9]  Xuan Zeng,et al.  Optimization and Quality Estimation of Circuit Design via Random Region Covering Method , 2017, ACM Trans. Design Autom. Electr. Syst..

[10]  Verena Marie Barthelmes,et al.  Profiling Occupant Behaviour in Danish Dwellings using Time Use Survey Data - Part II: Time-related Factors and Occupancy , 2018 .

[11]  Silvia Santini,et al.  Predicting household occupancy for smart heating control: A comparative performance analysis of state-of-the-art approaches , 2014 .

[12]  Tianzhen Hong,et al.  Simulation of occupancy in buildings , 2015 .

[13]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[14]  Mary Ann Piette,et al.  Data fusion in predicting internal heat gains for office buildings through a deep learning approach , 2019, Applied Energy.

[15]  Zheng Liu,et al.  Occupancy prediction model for open-plan offices using real-time location system and inhomogeneous Markov chain , 2019, Building and Environment.

[16]  Da Yan,et al.  Occupancy data at different spatial resolutions: Building energy performance and model calibration , 2021, Applied Energy.

[17]  H. Burak Gunay,et al.  Clustering and motif identification for occupancy-centric control of an air handling unit , 2020 .

[18]  Dimitrios Tzovaras,et al.  A context-aware method for building occupancy prediction , 2016 .

[19]  Kwang Ryel Ryu,et al.  Real-time occupancy prediction in a large exhibition hall using deep learning approach , 2019, Energy and Buildings.

[20]  Jin Dong,et al.  Occupancy-Based HVAC Control with Short-Term Occupancy Prediction Algorithms for Energy-Efficient Buildings , 2018, Energies.

[21]  Geoffrey Qiping Shen,et al.  Occupancy data analytics and prediction: A case study , 2016 .

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Sicheng Zhan,et al.  Building occupancy and energy consumption: Case studies across building types , 2021 .

[24]  Chen Zhe,et al.  Extracting typical occupancy data of different buildings from mobile positioning data , 2018, Energy and Buildings.

[25]  Cheol-Soo Park,et al.  Correlation between occupants and energy consumption , 2016 .

[26]  Yuan Jin,et al.  A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development , 2020, Building Simulation.

[27]  Zhenghua Chen,et al.  Comparing occupancy models and data mining approaches for regular occupancy prediction in commercial buildings , 2017 .

[28]  Da Yan,et al.  Typical weekly occupancy profiles in non-residential buildings based on mobile positioning data , 2021 .

[29]  Melissa M. Bilec,et al.  On-Site Renewable Energy and Green Buildings: A System-Level Analysis. , 2016, Environmental science & technology.

[30]  Wei Wang,et al.  Modeling and predicting occupancy profile in office space with a Wi-Fi probe-based Dynamic Markov Time-Window Inference approach , 2017 .

[31]  Jimeno A. Fonseca,et al.  Impacts of diversity in commercial building occupancy profiles on district energy demand and supply , 2020 .

[32]  Hao Yu,et al.  Distributed Machine Learning on Smart-Gateway Network toward Real-Time Smart-Grid Energy Management with Behavior Cognition , 2018, ACM Trans. Design Autom. Electr. Syst..

[33]  Skipper Seabold,et al.  Statsmodels: Econometric and Statistical Modeling with Python , 2010, SciPy.

[34]  Adam Glowacz,et al.  IoT Based Smart Parking System Using Deep Long Short Memory Network , 2020, Electronics.

[35]  Long Bao Le,et al.  Joint Optimization of Electric Vehicle and Home Energy Scheduling Considering User Comfort Preference , 2014, IEEE Transactions on Smart Grid.

[36]  Tianzhen Hong,et al.  The human dimensions of energy use in buildings: A review , 2018 .

[37]  Jeffrey S. Vipperman,et al.  Incorporation of scheduling and adaptive historical data in the Sensor-Utility-Network method for occupancy estimation , 2013 .

[38]  Da Yan,et al.  Building occupancy forecasting: A systematical and critical review , 2021 .

[39]  Gunnar Karlsson,et al.  Survey of Non-Image-Based Approaches for Counting People , 2020, IEEE Communications Surveys & Tutorials.

[40]  D. Fosas,et al.  Indoor environment quality and work performance in “green” office buildings in the Middle East , 2020, Building Simulation.

[41]  Hong Zhang,et al.  Agent-based modeling and simulation of stochastic heat pump usage behavior in residential communities , 2020 .

[42]  Ann Nowé,et al.  Nonparametric user activity modelling and prediction , 2020, User Modeling and User-Adapted Interaction.

[43]  Bauke de Vries,et al.  Methods for the prediction of intermediate activities by office occupants , 2010 .

[44]  P Pieter-Jan Hoes,et al.  Occupant behavior in identical residential buildings: A case study for occupancy profiles extraction and application to building performance simulation , 2019, Building Simulation.

[45]  Zoltán Nagy,et al.  Introducing IEA EBC annex 79: Key challenges and opportunities in the field of occupant-centric building design and operation , 2020, Building and Environment.

[46]  Peter W. Newton,et al.  Hybrid buildings: a pathway to carbon neutral housing , 2010 .

[47]  Arno Schlueter,et al.  A novel population-based occupancy modeling approach for district-scale simulations compared to standard-based methods , 2020, Building and Environment.

[48]  Mikkel Baun Kjærgaard,et al.  Performance comparison of occupancy count estimation and prediction with common versus dedicated sensors for building model predictive control , 2017 .

[49]  Weixin Huang,et al.  Modeling and predicting the occupancy in a China hub airport terminal using Wi-Fi data , 2019, Energy and Buildings.

[50]  Angela Lee,et al.  The impact of occupants’ behaviours on building energy analysis: A research review , 2017 .

[51]  Olivia Guerra-Santin,et al.  Comparing the impact of presence patterns on energy demand in residential buildings using measured data and simulation models , 2019, Building Simulation.

[52]  Fu Xiao,et al.  Quantifying uncertainty in the aggregate energy flexibility of high-rise residential building clusters considering stochastic occupancy and occupant behavior , 2020 .

[53]  Amin Hammad,et al.  Sensitivity analysis of probabilistic occupancy prediction model using big data , 2020 .

[54]  Talal Rahwan,et al.  Automatic HVAC Control with Real-time Occupancy Recognition and Simulation-guided Model Predictive Control in Low-cost Embedded System , 2017, ArXiv.